© 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. 91444
    Prev
    Next
    INDEX
    Explanations

    Exploitation, Abuse & Endangerment warnings

    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
    志森
    0.52
    دأ
    0.48
    IDENT
    0.48
    Identification
    0.46
    ман
    0.45
    BRAND
    0.45
    éléments
    0.45
    
    0.44
    Кон
    0.44
     বসু
    0.44
    POSITIVE LOGITS
     but
    0.56
     तुला
    0.48
     female
    0.46
    butan
    0.46
     Tuesday
    0.45
     male
    0.44
     Kamu
    0.44
    but
    0.44
     and
    0.44
     saw
    0.43
    Activations Density 0.016%

    No Known Activations