© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2181
    Prev
    Next
    INDEX
    Explanations

    table method

    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_40_width_65k_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
    olojik
    0.32
    ⸩
    0.31
    ч
    0.30
    ду
    0.29
    ്യ
    0.29
    უს
    0.29
    艘
    0.29
     których
    0.28
    urous
    0.28
     donn
    0.28
    POSITIVE LOGITS
     extraordinaire
    0.44
    における
    0.36
    /-
    0.35
     alone
    0.35
     enorme
    0.34
    および
    0.33
     (%
    0.33
     aka
    0.32
     இலங்க
    0.31
     నేపథ్యంలో
    0.31
    Activations Density 2.248%

    No Known Activations