© 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. 27294
    Prev
    Next
    INDEX
    Explanations

    philosophical substance

    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
    </em>
    0.62
    lə
    0.60
    고
    0.60
    ᅦ
    0.60
    a
    0.59
    అ
    0.57
    도
    0.57
    də
    0.57
    talent
    0.56
    {
    0.56
    POSITIVE LOGITS
    ဂျ
    0.57
     or
    0.52
    uk
    0.52
    avy
    0.50
     Many
    0.49
    uel
    0.49
    ell
    0.47
     چیک
    0.47
    clesi
    0.46
     parades
    0.46
    Activations Density 0.000%

    No Known Activations