INDEX

Explanations

tamoxifen, tampered, tamariscina, tammar

np_acts-logits-general · gemini-2.5-flash-lite

The neuron activates on the word "tam" which appears to be the beginning of words like "tamoxifen" in medical contexts or words like "tamper" or "template" in various texts.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

This neuron activates on occurrences of the substring “tam” (e.g. in words like “tamoxifen”).

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 และ

-2.42

And

-2.39

 Which

-2.36

はその

-2.33

Now

-2.33



-2.22

The

-2.22

transporte

-2.20

蝈

-2.19

 ซึ่ง

-2.14

POSITIVE LOGITS

3.05

焢

2.50

 意思

2.36

珢

2.33

銩

2.30

2.25

鋨

2.19

鉭

2.17

и

2.13

只有

2.11

Activations Density 0.001%

tamoxifen, tampered, tamariscina, tammar

The neuron activates on the word "tam" which appears to be the beginning of words like "tamoxifen" in medical contexts or words like "tamper" or "template" in various texts.

This neuron activates on occurrences of the substring “tam” (e.g. in words like “tamoxifen”).

No Comments

No Known Activations

tamoxifen, tampered, tamariscina, tammar

The neuron activates on the word "tam" which appears to be the beginning of words like "tamoxifen" in medical contexts or words like "tamper" or "template" in various texts.

This neuron activates on occurrences of the substring “tam” (e.g. in words like “tamoxifen”).

No Comments

No Known Activations