© 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. 34-GEMMASCOPE-RES-131K
    7. 107329
    Prev
    Next
    INDEX
    Explanations

    Fordham Road

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

    The neuron is responding to very common, high‐frequency function tokens (like the possessive ’s, tiny prepositions “in,” “at,” punctuation, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ⋯
    -0.92
     */}
    -0.85
    ▾
    -0.85
    </s>
    -0.81
    –
    -0.81
    ,:);
    -0.80
     Händ
    -0.77
    classNames
    -0.76
    －
    -0.75
    </u>
    -0.73
    POSITIVE LOGITS
     vinculado
    0.90
     ligado
    0.81
     příslu
    0.81
     sugerencias
    0.79
     Croatian
    0.78
     škola
    0.77
    sego
    0.77
     desempe
    0.76
    âme
    0.75
     velikost
    0.73
    Activations Density 0.323%

    No Known Activations