© 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. 136331
    Prev
    Next
    INDEX
    Explanations

    laying out explanations

    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
    ↵↵
    0.44
     bearer
    0.41
     lands
    0.41
    out
    0.41
    dip
    0.41
     audiov
    0.40
     flamboyant
    0.40
    web
    0.40
     complic
    0.40
     uppermost
    0.40
    POSITIVE LOGITS
    荕
    0.49
     quantità
    0.46
     പരിശീല
    0.46
     või
    0.45
     мероприятий
    0.45
     tanpa
    0.45
     sprzę
    0.44
    टू
    0.44
     κάθε
    0.44
     fără
    0.43
    Activations Density 0.004%

    No Known Activations