© 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-65K
    7. 15621
    Prev
    Next
    INDEX
    Explanations

    average eligibility criteria

    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_65k_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
    Ր
    0.52
    న్
    0.48
     హ
    0.47
     ಮ
    0.46
     Św
    0.46
    แบ
    0.45
    烺
    0.44
     特許
    0.44
     keç
    0.44
     ἐν
    0.43
    POSITIVE LOGITS
     usual
    0.40
    average
    0.40
    xml
    0.39
    www
    0.39
     Specialists
    0.38
    ranno
    0.38
     determinado
    0.38
    email
    0.38
     analyzes
    0.38
     determined
    0.37
    Activations Density 0.062%

    No Known Activations