© 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. 174625
    Prev
    Next
    INDEX
    Explanations

    no risk, lose quality, a new

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

    explaining relevance of concepts

    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
    पेड
    0.47
    segaretro
    0.46
    गिंग
    0.45
     έχ
    0.44
    recyclerView
    0.44
     能
    0.43
    كمان
    0.43
    మయ్య
    0.43
     Cec
    0.42
    డిన
    0.42
    POSITIVE LOGITS
     discretization
    0.48
     autopsy
    0.47
    arkt
    0.47
    (
    0.47
     be
    0.46
    <0x95>
    0.45
    裏
    0.43
     par
    0.43
    合い
    0.43
    analisi
    0.43
    Activations Density 0.000%

    No Known Activations