© 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. 68480
    Prev
    Next
    INDEX
    Explanations

    proof that or of

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

    proof that

    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
    elementary
    0.53
    eg
    0.53
    il
    0.52
    ar
    0.52
    w
    0.52
    examples
    0.50
    <0xE3>
    0.50
    art
    0.49
    particular
    0.49
    im
    0.49
    POSITIVE LOGITS
     αλλά
    0.53
     ଆ
    0.50
     进行
    0.50
     🙌
    0.50
     လ
    0.49
     hướng
    0.48
     computeEncoder
    0.47
     କ
    0.47
     mahi
    0.47
     那麼
    0.46
    Activations Density 0.006%

    No Known Activations