© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99672
    Prev
    Next
    INDEX
    Explanations

    French, art, security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Σ
    0.54
     QnrB
    0.51
    žil
    0.46
    ATIVA
    0.46
    iqueness
    0.45
     féidir
    0.45
    indazol
    0.44
    inig
    0.44
    சிற
    0.44
    watchlist
    0.44
    POSITIVE LOGITS
    ↵
    0.58
    ры
    0.50
     temptation
    0.50
     chiffre
    0.49
     a
    0.49
     marchand
    0.48
     apparten
    0.48
     figure
    0.47
     canvas
    0.46
     Renaissance
    0.46
    Activations Density 0.002%

    No Known Activations