© 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. 150291
    Prev
    Next
    INDEX
    Explanations

    account suspension

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

    specific research and plans

    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
    usal
    0.52
    itale
    0.52
    䒨
    0.47
    ulk
    0.46
    ዎን
    0.46
    ઓમાં
    0.46
    ened
    0.45
    <0xB8>
    0.45
    oire
    0.45
    intégr
    0.44
    POSITIVE LOGITS
     grammar
    0.48
    স্থা
    0.46
     unambiguously
    0.46
     vlast
    0.46
    個別
    0.45
     spolu
    0.44
    明確
    0.43
     receitas
    0.42
     građ
    0.42
     تريد
    0.42
    Activations Density 0.002%

    No Known Activations