© 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-16K
    7. 12484
    Prev
    Next
    INDEX
    Explanations

    forming or established components

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

    form or format

    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_16k_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
    ה
    0.96
     to
    0.80
    to
    0.76
    IE
    0.75
    cı
    0.75
     by
    0.72
     in
    0.71
    ING
    0.71
    p
    0.68
     havoc
    0.67
    POSITIVE LOGITS
     गठन
    0.92
     μορ
    0.88
    形成
    0.86
     गठित
    0.84
     formée
    0.84
     formed
    0.83
    形式
    0.82
     форми
    0.81
     গঠিত
    0.79
     FormGroup
    0.77
    Activations Density 0.205%

    No Known Activations