© 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. 13231
    Prev
    Next
    INDEX
    Explanations

    language and regions

    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
    ОВА
    0.53
    음에
    0.48
    basicConfig
    0.47
    arlama
    0.46
    彫
    0.46
    揮
    0.45
    <unused72>
    0.45
     паци
    0.43
    獷
    0.43
     செயலாளர்
    0.43
    POSITIVE LOGITS
    s
    0.49
    、
    0.49
     voisins
    0.44
    ↵↵
    0.42
    in
    0.42
     genutzt
    0.41
     dandelion
    0.40
     standaard
    0.40
    ↵
    0.39
     mountains
    0.39
    Activations Density 0.003%

    No Known Activations