© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103847
    Prev
    Next
    INDEX
    Explanations

    properties, qualities, value

    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_16_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
    অ্যাপ
    0.50
    ﺙ
    0.49
    ’
    0.48
     thy
    0.47
    써
    0.46
    সার
    0.45
    Erro
    0.44
     sổ
    0.44
    ナナ
    0.44
    Signin
    0.43
    POSITIVE LOGITS
    em
    0.53
    lights
    0.52
     විශ්
    0.52
    luft
    0.50
    life
    0.49
    ut
    0.48
    uş
    0.47
    funny
    0.47
     }).
    0.47
    efficients
    0.46
    Activations Density 0.000%

    No Known Activations