© 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. 204860
    Prev
    Next
    INDEX
    Explanations

    open source implementation

    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
     récupération
    0.43
     parol
    0.41
    🥒
    0.40
     golden
    0.39
    ार्ज
    0.38
    addSql
    0.38
    massage
    0.38
    ᚖ
    0.38
     recuperar
    0.37
    ющими
    0.37
    POSITIVE LOGITS
     rallied
    0.41
    TOK
    0.41
    SELF
    0.35
    CO
    0.34
    LV
    0.34
    WA
    0.34
    运气
    0.34
     Coordinator
    0.34
    시다
    0.34
    Un
    0.33
    Activations Density 0.001%

    No Known Activations