© 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. 201003
    Prev
    Next
    INDEX
    Explanations

    from and to

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

    develop HTML

    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
    getMonth
    0.46
    тоо
    0.42
     solidly
    0.42
    addElement
    0.39
    户外
    0.39
     Reinigung
    0.39
    }}}+\
    0.38
    穗
    0.38
    戶
    0.37
    frames
    0.37
    POSITIVE LOGITS
    🥔
    0.53
    கு
    0.49
     অথ
    0.49
    س
    0.49
     annotated
    0.48
    مو
    0.48
    د
    0.46
     Biom
    0.46
    குதியில்
    0.46
     productor
    0.45
    Activations Density 0.001%

    No Known Activations