© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 12972
    Prev
    Next
    INDEX
    Explanations

    examples and potential outcomes

    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
    SERVER
    0.45
    ModeBanner
    0.43
    }},
    0.42
    ang
    0.42
    ipo
    0.41
    ård
    0.40
     पदार्थ
    0.40
     sering
    0.40
    ai
    0.40
     sirve
    0.40
    POSITIVE LOGITS
    例如
    0.49
     aston
    0.48
    <unused18>
    0.46
    쿱
    0.46
     questioned
    0.45
    合理的
    0.45
    テゴ
    0.44
    火
    0.44
    箜
    0.44
    大会
    0.43
    Activations Density 0.001%

    No Known Activations