© 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. 31-GEMMASCOPE-2-RES-262K
    7. 7618
    Prev
    Next
    INDEX
    Explanations

    points for consideration

    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_31_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
     was
    0.24
     an
    0.23
     one
    0.23
     is
    0.22
     be
    0.21
    LE
    0.21
     "
    0.20
    RE
    0.20
    本身
    0.20
    RES
    0.20
    POSITIVE LOGITS
     связанные
    0.30
     dotyczące
    0.29
     privind
    0.29
     которые
    0.28
     concernant
    0.28
     факторы
    0.28
     neler
    0.27
     relacionadas
    0.27
     щодо
    0.25
     esigenze
    0.25
    Activations Density 1.508%

    No Known Activations