© 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. 865
    Prev
    Next
    INDEX
    Explanations

    detailed skill description

    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
    ید
    0.51
    ون
    0.50
    א
    0.49
    ко
    0.46
    .
    0.45
    המ
    0.45
    어로
    0.44
    ה
    0.44
    ши
    0.44
    ী
    0.44
    POSITIVE LOGITS
     is
    0.89
     of
    0.78
    s
    0.71
     at
    0.70
     t
    0.64
     a
    0.62
    \
    0.60
     to
    0.56
     s
    0.55
     was
    0.55
    Activations Density 0.065%

    No Known Activations