© 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. 75871
    Prev
    Next
    INDEX
    Explanations

    damage or heat

    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
    裒
    0.49
     saúde
    0.48
    濋
    0.47
     Saúde
    0.46
     Arzneim
    0.46
     Pharmacology
    0.46
     filas
    0.45
     portas
    0.45
     tumult
    0.44
    휋
    0.44
    POSITIVE LOGITS
    lijke
    0.52
    application
    0.51
     damaged
    0.51
    executed
    0.51
    dalam
    0.49
    configured
    0.49
    id
    0.48
    execution
    0.48
    launched
    0.48
    nik
    0.48
    Activations Density 0.006%

    No Known Activations