© 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. 111958
    Prev
    Next
    INDEX
    Explanations

    the one

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

    queen elizabeth

    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
    㞒
    0.54
    㞔
    0.54
     funkce
    0.52
    䐂
    0.52
     einsch
    0.51
    Église
    0.49
     henkil
    0.49
    尌
    0.49
    řit
    0.48
     機能
    0.48
    POSITIVE LOGITS
    ا
    0.52
    quen
    0.50
    os
    0.48
    u
    0.46
     monomers
    0.44
     quant
    0.44
     Quant
    0.44
     favoured
    0.44
    و
    0.44
     cones
    0.43
    Activations Density 0.000%

    No Known Activations