© 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. 169864
    Prev
    Next
    INDEX
    Explanations

    yogurt Paste Bans

    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
    ли
    0.49
     Tipo
    0.47
     contenidos
    0.46
    <0x06>
    0.45
    Tipo
    0.45
     صہی
    0.45
    ።
    0.44
    
    0.44
    タイプ
    0.44
    全体
    0.44
    POSITIVE LOGITS
     thermal
    0.50
     ot
    0.45
     agat
    0.44
     regl
    0.44
     Church
    0.44
    Baker
    0.44
     za
    0.43
    brake
    0.43
     wat
    0.42
     et
    0.42
    Activations Density 0.006%

    No Known Activations