© 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. 6305
    Prev
    Next
    INDEX
    Explanations

    man-hour or repairman

    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
    in
    2.52
    د
    2.27
    d
    2.23
    as
    2.11
    p
    1.91
     to
    1.91
    to
    1.91
    k
    1.88
    g
    1.88
    u
    1.81
    POSITIVE LOGITS
    ва
    1.75
    ен
    1.34
    ет
    1.19
     crouching
    1.17
    ер
    1.13
     σε
    1.11
    εται
    1.05
     которыми
    1.03
    ве
    1.02
     puisse
    1.02
    Activations Density 0.061%

    No Known Activations