© 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. 128707
    Prev
    Next
    INDEX
    Explanations

    deep conversation or harmful

    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
     calmed
    0.50
     istit
    0.46
    ਾਕ
    0.46
     sentito
    0.46
    轳
    0.46
    ുവരി
    0.45
    ิล
    0.44
    она
    0.44
    iqui
    0.44
     adapters
    0.44
    POSITIVE LOGITS
    mend
    0.47
    '}
    0.46
    ').
    0.46
    机
    0.45
     encont
    0.45
     اچ
    0.43
    ')
    0.43
     своих
    0.43
    丳
    0.43
     Sekret
    0.42
    Activations Density 0.003%

    No Known Activations