© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14925
    Prev
    Next
    INDEX
    Explanations

    measurements and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    หมือน
    3.08
    чего
    2.89
    chyné
    2.84
    न्होंने
    2.82
    俩
    2.80
    มี
    2.63
    Pieces
    2.55
    जेंसी
    2.53
    เสีย
    2.52
     органы
    2.50
    POSITIVE LOGITS
    ines
    2.06
    sent
    1.95
    beis
    1.88
     gut
    1.88
    ief
    1.87
     stra
    1.86
    hum
    1.80
    spray
    1.76
     fluff
    1.69
    e
    1.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.