Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 138189
    Prev
    Next
    INDEX
    Explanations

    octave

    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
    >
    1.60
    ות
    1.54
    ;
    1.37
    ین
    1.23
    ,
    1.23
    ਹ
    1.20
     exquisitely
    1.16
     legumes
    1.16
     a
    1.14
     escapes
    1.12
    POSITIVE LOGITS
    s
    1.51
    c
    1.44
    for
    1.34
    on
    1.22
    parameter
    1.11
    that
    1.09
    decimal
    1.09
     For
    1.07
    oct
    1.06
    term
    1.05
    Activations Density 0.003%

    No Known Activations