© 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. 36059
    Prev
    Next
    INDEX
    Explanations

    preach Gospel, prove this

    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
    velles
    0.43
    álás
    0.42
    ý
    0.42
    erton
    0.42
    area
    0.41
    leaf
    0.41
     fí
    0.40
    ende
    0.40
    ümüş
    0.38
     केलं
    0.37
    POSITIVE LOGITS
     möglichst
    0.44
    哧
    0.40
     forbids
    0.39
     যাবতীয়
    0.38
    规模
    0.35
    ह्म
    0.34
     বদ্ধ
    0.34
     बतौर
    0.34
     quarters
    0.34
     गैर
    0.33
    Activations Density 0.003%

    No Known Activations