© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 40754
    Prev
    Next
    INDEX
    Explanations

    logout actions or scripts

    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
    ?
    0.82
     
    0.80
    (
    0.73
     birefringence
    0.70
    !
    0.70
     spectrogram
    0.67
     infrastructure
    0.66
    ,《
    0.65
    %!
    0.65
    ført
    0.64
    POSITIVE LOGITS
    is
    0.97
    as
    0.91
    ci
    0.87
    il
    0.86
    ла
    0.85
    os
    0.84
    im
    0.82
    or
    0.80
    al
    0.80
    tted
    0.80
    Activations Density 0.001%

    No Known Activations