© 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. 21211
    Prev
    Next
    INDEX
    Explanations

    livelihoods, alkaloids, likelihood

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

    words related to livelihoods and substances like alkaloids.

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

    The neuron activates on occurrences of the word “livelihood” (including its plural form).

    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
    ꜆
    -2.67
    of
    -2.55
    </i>
    -2.48
    Ꮗ
    -2.39
    la
    -2.38
    釙
    -2.22
    壜
    -2.22
    ي
    -2.22
    íg
    -2.14
    嫫
    -2.14
    POSITIVE LOGITS
    ﻊ
    2.59
    <bos>
    2.59
    但
    2.20
    Función
    2.09
    opcional
    2.08
                
    2.06
     anstatt
    2.03
    código
    1.98
    this
    1.97
     оо
    1.97
    Activations Density 0.001%

    No Known Activations