© 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. 137880
    Prev
    Next
    INDEX
    Explanations

    repository, PANDAS, purple, war

    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
    ס
    0.77
    ку
    0.59
    ק
    0.57
    ،
    0.51
    et
    0.50
    ート
    0.49
    с
    0.49
    на
    0.48
    დ
    0.48
     compartments
    0.48
    POSITIVE LOGITS
    MEM
    0.43
    SEN
    0.42
    TEM
    0.42
    OCT
    0.42
    Gloss
    0.42
    GET
    0.41
    ennem
    0.40
     MEM
    0.40
     জমা
    0.40
     IMPACT
    0.40
    Activations Density 0.001%

    No Known Activations