© 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. 59304
    Prev
    Next
    INDEX
    Explanations

    each individual branch

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

    calculable function

    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
    y
    0.44
    s
    0.43
    mation
    0.42
    ist
    0.41
     information
    0.40
    是因為
    0.40
    患
    0.40
     ने
    0.39
    information
    0.38
    際には
    0.38
    POSITIVE LOGITS
     industriel
    0.47
     dowol
    0.45
     pohon
    0.44
    FlashValue
    0.43
     pajak
    0.43
    がたくさん
    0.43
     każdym
    0.43
     industriales
    0.43
    ㏄
    0.43
     plupart
    0.42
    Activations Density 0.000%

    No Known Activations