© 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. 71784
    Prev
    Next
    INDEX
    Explanations

    beneficiaries, paralysis, depreciation

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

    formatting with bold markers

    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
    $
    0.49
     counterclaim
    0.49
    ultat
    0.45
    frag
    0.45
    valuation
    0.44
     idiosyncratic
    0.44
    ценка
    0.44
     presenti
    0.44
     pointless
    0.43
     modulating
    0.43
    POSITIVE LOGITS
    يا
    0.54
    Rajas
    0.47
    Dairy
    0.47
     各
    0.46
    دي
    0.46
     แรก
    0.45
    adobe
    0.45
    וי
    0.45
    ৪৪
    0.44
    кість
    0.43
    Activations Density 0.001%

    No Known Activations