© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 233214
    Prev
    Next
    INDEX
    Explanations

    community generation understanding presentation Samsung Galaxy drawing

    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
    rs
    0.56
    ḳ
    0.56
    nicht
    0.53
    delayed
    0.52
    funktion
    0.49
    swt
    0.48
     baguette
    0.47
    er
    0.47
    paris
    0.47
    ration
    0.46
    POSITIVE LOGITS
    今天要
    0.47
     escolas
    0.46
     हैं
    0.46
    车
    0.46
     avevano
    0.46
     були
    0.45
     presenti
    0.44
     indicadores
    0.44
     thóc
    0.43
    轴
    0.43
    Activations Density 0.000%

    No Known Activations