© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56649
    Prev
    Next
    INDEX
    Explanations

    predictive outcomes and consequences

    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
    к
    0.46
    ise
    0.46
    狯
    0.45
    Camel
    0.45
     caballo
    0.44
     badania
    0.44
    два
    0.44
     полное
    0.44
    क
    0.44
    मराह
    0.44
    POSITIVE LOGITS
     fuelled
    0.49
     configured
    0.47
     neighbouring
    0.46
     deiner
    0.46
     ambient
    0.45
     configuring
    0.45
     defines
    0.45
     normales
    0.44
     occasioned
    0.44
     surrounding
    0.43
    Activations Density 0.003%

    No Known Activations