© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11155
    Prev
    Next
    INDEX
    Explanations

    things to avoid

    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
     Isi
    0.52
    ிறது
    0.52
    ிருந்தது
    0.52
     Sicilian
    0.49
     Bolog
    0.46
     lluvia
    0.46
    🥲
    0.46
     Natasha
    0.46
    ianSpace
    0.45
    فی
    0.45
    POSITIVE LOGITS
    Votes
    0.46
    函
    0.46
    posals
    0.46
    FORMANCE
    0.43
    ajte
    0.40
    পোষ
    0.40
     ট
    0.40
     Arrangement
    0.38
    ндарт
    0.38
    करिता
    0.38
    Activations Density 0.001%

    No Known Activations