© 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. 154621
    Prev
    Next
    INDEX
    Explanations

    public events, local subsidiaries, brand development

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

    repeated exposure or injections

    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
    uisce
    0.48
    acons
    0.48
    claration
    0.47
    tank
    0.46
    assembling
    0.46
    近
    0.46
    configure
    0.45
    detector
    0.45
    bytecode
    0.45
    hd
    0.45
    POSITIVE LOGITS
     D
    0.58
     A
    0.57
     y
    0.56
     Pass
    0.56
     G
    0.54
     Gel
    0.53
     Guel
    0.53
     Mayo
    0.52
     Link
    0.52
     I
    0.52
    Activations Density 0.000%

    No Known Activations