© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221963
    Prev
    Next
    INDEX
    Explanations

    toxic reaction, haunting cemeteries, require much

    np_acts-logits-general · gemini-2.5-flash-lite

    access and navigate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ነት
    0.55
    י
    0.54
     الهمزه
    0.52
    पदी
    0.52
     ocurrido
    0.52
    ي
    0.52
    フト
    0.51
    ریان
    0.50
    कालीन
    0.48
    ход
    0.48
    POSITIVE LOGITS
     spearheaded
    0.57
     Sena
    0.50
    amp
    0.48
    the
    0.48
     布
    0.48
     etched
    0.48
    vred
    0.48
     offered
    0.48
    you
    0.47
     Excellent
    0.46
    Activations Density 0.000%

    No Known Activations