Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8923
    Prev
    Next
    INDEX
    Explanations

    SAFE

    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
     Middleware
    0.34
     intellectuals
    0.31
    鋈
    0.31
    譞
    0.31
     markup
    0.30
     Electrochemical
    0.30
     overfitting
    0.30
     solvation
    0.30
     عرصے
    0.29
    ماً
    0.28
    POSITIVE LOGITS
    Full
    0.32
     пъ
    0.32
    【
    0.29
    IGH
    0.28
    LIN
    0.28
    「
    0.28
    ER
    0.28
    ῾
    0.28
    in
    0.28
    car
    0.28
    Activations Density 0.011%

    No Known Activations