© 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. 22-GEMMASCOPE-RES-131K
    7. 71060
    Prev
    Next
    INDEX
    Explanations

    words following quotation marks or punctuation

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

    The neuron activates on numeric tokens (digits or numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -1.06
     When
    -1.05
    TokenNameDOT
    -1.04
    靄
    -1.02
     During
    -1.02
     potret
    -1.00
    inverno
    -0.97
    🧝
    -0.96
    anera
    -0.93
    thoven
    -0.92
    POSITIVE LOGITS
     then
    1.31
    を追加
    1.12
    にとっては
    1.08
     będę
    1.08
     NEGRO
    1.05
     tejidos
    1.05
    )");
    1.05
    ]));
    1.05
    </blockquote>
    1.03
     cerrados
    1.03
    Activations Density 0.005%

    No Known Activations