© 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. 134661
    Prev
    Next
    INDEX
    Explanations

    significant business or legal terms

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

    web addresses and technical terms

    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
     Боли
    0.62
     составля
    0.55
     specifiche
    0.54
     Egipto
    0.53
     忄
    0.50
     Mitra
    0.49
     primarySwatch
    0.49
    ้วน
    0.49
     Архі
    0.48
     Архи
    0.48
    POSITIVE LOGITS
    RE
    0.52
    SS
    0.48
    <0xA9>
    0.47
    昆
    0.47
    WHAT
    0.46
    ân
    0.45
    prd
    0.45
    TOR
    0.44
    阻止
    0.44
    9
    0.44
    Activations Density 0.001%

    No Known Activations