© 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. 85974
    Prev
    Next
    INDEX
    Explanations

    Black Lives Matter or B2B

    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
    0.73
     greetings
    0.55
     all
    0.55
    id
    0.54
    MN
    0.52
    ften
    0.51
    (
    0.51
     I
    0.51
    All
    0.49
     V
    0.48
    POSITIVE LOGITS
    ту
    0.70
    на
    0.68
    كين
    0.64
    ну
    0.63
    сур
    0.63
    су
    0.63
     czerwca
    0.61
    と
    0.61
    кл
    0.60
    фан
    0.60
    Activations Density 0.001%

    No Known Activations