© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184336
    Prev
    Next
    INDEX
    Explanations

    heart attack

    np_acts-logits-general · gemini-2.5-flash-lite

    constraints such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    编号
    0.47
    靘
    0.46
     थे
    0.46
    瀏
    0.46
     radionu
    0.46
     anions
    0.45
     ਵਾਲ
    0.45
    読
    0.45
    ቓ
    0.45
     UserDefaults
    0.44
    POSITIVE LOGITS
    D
    0.61
    R
    0.50
    га
    0.46
    тива
    0.45
    Z
    0.45
    rightarrow
    0.45
    G
    0.45
    effect
    0.44
    widehat
    0.44
    Permission
    0.44
    Activations Density 0.002%

    No Known Activations