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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28365
    Prev
    Next
    INDEX
    Explanations

    different kinds

    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
     стоковое
    0.50
    絘
    0.48
     акчага
    0.48
    荞
    0.47
    鹦
    0.47
     protéines
    0.47
    螫
    0.47
    蕨
    0.47
    BlockFit
    0.46
    ChartView
    0.46
    POSITIVE LOGITS
    e
    0.58
    -
    0.57
    .
    0.56
    0
    0.52
    2
    0.52
    h
    0.51
    a
    0.49
    ,
    0.48
    ch
    0.48
    c
    0.46
    Activations Density 0.000%

    No Known Activations