© 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. 160931
    Prev
    Next
    INDEX
    Explanations

    organization, location, or official documents

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

    descriptive words, foreign languages

    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
     ο
    0.48
     с
    0.47
     ρ
    0.46
    爍
    0.46
     і
    0.46
     м
    0.45
    であ
    0.45
     incre
    0.44
     וב
    0.44
    Υ
    0.44
    POSITIVE LOGITS
     الملك
    0.47
    vény
    0.46
     recuperar
    0.46
    زين
    0.45
    Bună
    0.43
     numéro
    0.41
     ressort
    0.41
    äst
    0.41
     يجب
    0.40
    يي
    0.40
    Activations Density 0.000%

    No Known Activations