© 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. 79349
    Prev
    Next
    INDEX
    Explanations

    We are

    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
     billi
    0.50
     you
    0.46
     wanton
    0.44
     усили
    0.44
    ן
    0.43
     disso
    0.43
     rezultat
    0.43
     billiard
    0.43
    You
    0.43
    本次
    0.43
    POSITIVE LOGITS
     кеңсесинде
    0.47
    élite
    0.44
    økt
    0.44
    lications
    0.43
    гле
    0.43
     appellate
    0.43
    CNc
    0.42
     habitudes
    0.41
    }-\
    0.41
    ätze
    0.41
    Activations Density 0.002%

    No Known Activations