© 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. 69870
    Prev
    Next
    INDEX
    Explanations

    listing items

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

    referring to different meanings

    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
    или
    0.52
    inka
    0.50
    õ
    0.48
    inn
    0.48
    be
    0.48
    äk
    0.46
    hObject
    0.46
    which
    0.46
    sum
    0.45
    र
    0.44
    POSITIVE LOGITS
     propo
    0.51
     ganhou
    0.51
    StarObject
    0.50
     piezo
    0.47
     correa
    0.47
    ログイン
    0.46
     zostało
    0.46
     cappuccino
    0.46
     interessi
    0.46
     mandibular
    0.46
    Activations Density 0.000%

    No Known Activations