© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23994
    Prev
    Next
    INDEX
    Explanations

    description, name, champions, box

    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
    politik
    0.35
    proble
    0.33
    象征
    0.33
     незакон
    0.33
     disgraceful
    0.32
    诋
    0.31
    Neces
    0.31
    тири
    0.31
    悖
    0.31
    ЕР
    0.30
    POSITIVE LOGITS
     +
    0.38
     bytes
    0.35
     parameters
    0.32
     A
    0.31
     combined
    0.30
     composites
    0.30
     values
    0.30
     refined
    0.30
     and
    0.29
     String
    0.29
    Activations Density 0.279%

    No Known Activations