© 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. 44928
    Prev
    Next
    INDEX
    Explanations

    family history, stop loss, red ocean

    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
     डेब्यू
    0.48
     gençler
    0.47
     técnico
    0.45
    主义
    0.45
     लेटेस्ट
    0.44
    🄰
    0.44
    ünstler
    0.44
    parsedBlock
    0.43
    ancellationToken
    0.43
    不然
    0.43
    POSITIVE LOGITS
     that
    0.53
     unites
    0.50
     storage
    0.49
     accessing
    0.48
     I
    0.48
     integrates
    0.48
     lists
    0.48
     transforms
    0.47
     achieves
    0.46
     of
    0.46
    Activations Density 0.004%

    No Known Activations