© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128144
    Prev
    Next
    INDEX
    Explanations

    chickens and phosphorylation

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

    references to chickens and biochemical processes like phosphorylation.

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

    The neuron strongly responds to the word “chickens” (i.e. plural chicken mentions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    -3.23
    0
    -2.48
    ي
    -2.44
    3
    -2.33
    ра
    -2.31
    Now
    -2.22
     to
    -2.20
    What
    -2.19
    From
    -2.19
    This
    -2.16
    POSITIVE LOGITS
    癭
    2.97
    憷
    2.86
    镒
    2.38
    ꜆
    2.36
    謦
    2.34
    鴆
    2.33
     lidé
    2.27
    蠖
    2.27
    ftrag
    2.27
    廪
    2.25
    Activations Density 0.010%

    No Known Activations