© 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. 63750
    Prev
    Next
    INDEX
    Explanations

    states and conditions

    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
    बीसी
    0.50
    정과
    0.49
    DICTION
    0.49
    senior
    0.47
    OCITY
    0.46
    username
    0.45
    과
    0.45
     ਅਤੇ
    0.44
    :“
    0.44
    BSCRIBE
    0.44
    POSITIVE LOGITS
     épaules
    0.43
     Pip
    0.43
     Costs
    0.43
     magnificent
    0.40
    assertSame
    0.40
     costs
    0.40
     Pav
    0.40
     festgelegt
    0.40
     Benef
    0.39
     Harga
    0.39
    Activations Density 0.048%

    No Known Activations