© 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. 129003
    Prev
    Next
    INDEX
    Explanations

    original designs, this thesis, muscle tension

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

    contact information placeholders

    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
    Terms
    0.52
     anniversaire
    0.51
    いう
    0.50
     anivers
    0.50
    у
    0.48
     Terms
    0.47
     exécut
    0.47
     хра
    0.46
     назнача
    0.46
    ীষ্ম
    0.45
    POSITIVE LOGITS
    abhavo
    0.54
    oxidation
    0.52
    judul
    0.50
    void
    0.50
    gel
    0.48
    plate
    0.48
     township
    0.48
    derabad
    0.48
    finish
    0.47
    沍
    0.47
    Activations Density 0.000%

    No Known Activations