© 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. 217488
    Prev
    Next
    INDEX
    Explanations

    without treatment

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

    Drew Gooden

    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
     אותו
    0.42
     молодой
    0.40
     oranges
    0.39
    潘
    0.39
     tqdm
    0.38
     ಒಳ್ಳೆಯ
    0.37
     yellows
    0.37
     پت
    0.37
     barking
    0.37
    coles
    0.36
    POSITIVE LOGITS
    éraux
    0.48
    årt
    0.47
    Azure
    0.47
    ¿
    0.46
    aż
    0.45
    exposition
    0.45
    arów
    0.44
    histoire
    0.44
    nione
    0.42
    吨
    0.42
    Activations Density 0.001%

    No Known Activations