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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 6604
    Prev
    Next
    INDEX
    Explanations

    pani puri

    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_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
     foster
    0.47
    leeve
    0.43
     BOR
    0.38
     Bost
    0.37
     फड
    0.36
    象棋
    0.36
     Mahal
    0.36
    <unused9>
    0.35
    休み
    0.35
     placed
    0.35
    POSITIVE LOGITS
    Want
    0.39
    Send
    0.39
    Gi
    0.37
    Alessandro
    0.37
    要
    0.37
    hash
    0.36
    aporation
    0.36
    Ward
    0.35
    ወዳ
    0.35
    knię
    0.35
    Activations Density 0.001%

    No Known Activations