© 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-65K
    7. 20320
    Prev
    Next
    INDEX
    Explanations

    potential, forecasting, emotional, series

    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_65k_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
    0.25
    <0xE3>
    0.25
    。
    0.24
     professor
    0.24
     V
    0.23
     professors
    0.23
    <sup>
    0.23
     statue
    0.23
    -
    0.22
     No
    0.22
    POSITIVE LOGITS
     verificación
    0.28
    濵
    0.27
    chließlich
    0.26
    فيذ
    0.26
    Jährige
    0.26
     놓
    0.26
    ్రీన్
    0.26
    溇
    0.26
    ెండు
    0.25
    柅
    0.25
    Activations Density 0.000%

    No Known Activations