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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54287
    Prev
    Next
    INDEX
    Explanations

    middle initial or name

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

    The neuron fires on numeric tokens (digits and numbers) and closely related quantitative words (e.g. “middle,” “initial,” “between”).

    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
     at
    -0.80
    jsx
    -0.74
     five
    -0.70
     prevents
    -0.69
     grandmother
    -0.69
    エンド
    -0.69
    няются
    -0.69
    蓓
    -0.69
    qui
    -0.67
     penyakit
    -0.67
    POSITIVE LOGITS
    second
    0.95
    Secondly
    0.93
    🕝
    0.89
    糬
    0.85
    lesia
    0.85
     second
    0.85
    髫
    0.84
    第二个
    0.82
    жте
    0.81
     Polícia
    0.81
    Activations Density 0.048%

    No Known Activations