© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21456
    Prev
    Next
    INDEX
    Explanations

    City Council

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

    Summer savings, big results, love

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    d
    0.47
    s
    0.46
    required
    0.46
    id
    0.45
    ↵
    0.45
    es
    0.45
    "
    0.43
     "
    0.43
    ล
    0.43
     Key
    0.43
    POSITIVE LOGITS
     finalement
    0.51
     médiocrement
    0.50
     BETTER
    0.49
     condição
    0.49
    到来
    0.49
     importe
    0.48
    <unused42>
    0.48
     condições
    0.47
     चन्द्र
    0.47
     Lobkovic
    0.47
    Activations Density 0.000%

    No Known Activations