© 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. 124114
    Prev
    Next
    INDEX
    Explanations

    of [descriptive word]

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

    service account key

    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
     初
    0.53
     mutta
    0.48
     light
    0.47
     svjet
    0.47
     光
    0.45
     somewhat
    0.45
     Eksp
    0.44
     Vacuum
    0.43
     Prefecture
    0.43
     Bn
    0.42
    POSITIVE LOGITS
    ش
    0.51
    ﺶ
    0.47
    اگر
    0.46
    கால
    0.46
    चानक
    0.45
    ह
    0.45
    癥
    0.44
    ㅉ
    0.43
    ح
    0.43
    Stranger
    0.43
    Activations Density 0.001%

    No Known Activations