© 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. 193928
    Prev
    Next
    INDEX
    Explanations

    Octopus account

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

    ironically or expressing nuance

    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
     the
    0.57
     triples
    0.47
    at
    0.47
    年
    0.46
     hyper
    0.46
     LEGO
    0.45
     handheld
    0.45
     YEAR
    0.45
     evaporator
    0.44
     NCA
    0.44
    POSITIVE LOGITS
    FLP
    0.50
    Ga
    0.49
     पॉलिटी
    0.47
    Мне
    0.46
     Flugh
    0.46
    Ң
    0.46
     गवा
    0.45
     Breck
    0.45
     Bitte
    0.45
    comme
    0.44
    Activations Density 0.000%

    No Known Activations