© 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. 61970
    Prev
    Next
    INDEX
    Explanations

    out after certain words

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

    commits, size, genitals, security scores

    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
    ↵↵
    0.43
    または
    0.41
    と
    0.40
    ＆
    0.38
    棟
    0.38
    これにより
    0.37
    /
    0.37
    上げ
    0.36
    や
    0.36
    Й
    0.36
    POSITIVE LOGITS
     Waterloo
    0.38
    诗人
    0.38
     boyunca
    0.38
    했고
    0.37
     çeşitli
    0.36
     Đức
    0.36
    秫
    0.35
     Республики
    0.35
     Revue
    0.35
     যুবক
    0.35
    Activations Density 0.001%

    No Known Activations