© 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. 200149
    Prev
    Next
    INDEX
    Explanations

    often, slightly, multiple, several

    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
     швидко
    0.55
    Khokhlov
    0.54
    𝘼
    0.53
     раствора
    0.51
    츈
    0.50
     تباہ
    0.49
     aphids
    0.48
    癇
    0.48
     कैन
    0.46
     rarement
    0.46
    POSITIVE LOGITS
    it
    0.47
    as
    0.42
    }</
    0.42
    in
    0.42
    includes
    0.40
    details
    0.39
     US
    0.39
     appare
    0.38
    找不到
    0.38
    शै
    0.38
    Activations Density 0.004%

    No Known Activations