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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 98680
    Prev
    Next
    INDEX
    Explanations

    heavy threats and risks

    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
    ሽን
    0.40
     Silvia
    0.39
     Lucy
    0.37
    <unused98>
    0.37
    ৯
    0.37
    ૯
    0.37
     Nied
    0.37
    selling
    0.36
     মৌসুম
    0.35
     ות
    0.35
    POSITIVE LOGITS
    inches
    0.38
    悔
    0.37
    isVisible
    0.37
     따로
    0.37
     isothermal
    0.36
    左右
    0.36
     heavy
    0.35
     Antit
    0.35
     visible
    0.35
     Heavy
    0.35
    Activations Density 0.000%

    No Known Activations