© 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. 22391
    Prev
    Next
    INDEX
    Explanations

    charging, requiring, analyzing, cold

    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
     theses
    0.43
     cance
    0.38
    を開始
    0.38
     απε
    0.38
     our
    0.37
    API
    0.37
     we
    0.36
     別
    0.36
     API
    0.35
    фи
    0.35
    POSITIVE LOGITS
     ért
    0.43
    nın
    0.42
     ağırl
    0.42
    某个
    0.42
     expectant
    0.42
    álním
    0.42
    悌
    0.41
     trabajos
    0.40
     এমন
    0.40
     pekerjaan
    0.40
    Activations Density 0.000%

    No Known Activations