© 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. 122804
    Prev
    Next
    INDEX
    Explanations

    take XXX out/one/to/into

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

    text and images as inputs

    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
     a
    0.80
    d
    0.66
    ائ
    0.52
     the
    0.49
    ס
    0.48
    m
    0.48
    使用
    0.47
    ning
    0.47
     d
    0.46
    در
    0.46
    POSITIVE LOGITS
    ༣
    0.52
    CHARS
    0.50
    し
    0.49
    crose
    0.49
     اتارنا
    0.48
    tDBOutput
    0.47
    стую
    0.47
    ၃
    0.47
    ске
    0.46
    ).__
    0.46
    Activations Density 0.099%

    No Known Activations