© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86295
    Prev
    Next
    INDEX
    Explanations

    human and primates

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

    The neuron detects references to "human" or "humanity" in contexts related to dehumanization or distinguishing humans from non-humans.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    </h3>
    -2.22
     een
    -1.98
    闼
    -1.78
    ieuses
    -1.73
    ⧠
    -1.67
    щита
    -1.66
    ፨
    -1.66
    ﮦ
    -1.66
     tudi
    -1.64
    非常に
    -1.63
    POSITIVE LOGITS
    </b>
    2.14
    {
    2.02
    leggio
    1.77
    𝐇
    1.73
     a
    1.70
    垸
    1.69
    ן
    1.66
    woorden
    1.66
    㩒
    1.66
    chläge
    1.65
    Activations Density 0.006%

    No Known Activations