© 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. 189220
    Prev
    Next
    INDEX
    Explanations

    choppromotion

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

    Learning paths and resources

    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
    .
    0.52
    Π
    0.50
    ation
    0.48
    发生在
    0.47
    SON
    0.46
    塡
    0.46
    台湾
    0.44
    力的
    0.43
    ूले
    0.42
    odore
    0.42
    POSITIVE LOGITS
     materialize
    0.49
     specialize
    0.48
    ಾಯಿತು
    0.47
    »،
    0.47
    innerApiCalls
    0.47
    دت
    0.46
     infiltrated
    0.46
     personas
    0.46
     warranties
    0.45
     insulate
    0.45
    Activations Density 0.000%

    No Known Activations