© 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. 232194
    Prev
    Next
    INDEX
    Explanations

    Privacy lovers horrible

    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
     maxi
    0.49
     venezol
    0.49
    )/
    0.47
     columnName
    0.46
    ]/
    0.46
     postId
    0.46
     venous
    0.44
     aort
    0.44
    Fresh
    0.44
     law
    0.44
    POSITIVE LOGITS
    ๒
    0.49
    IKA
    0.48
    сько
    0.48
    ც
    0.48
    avier
    0.45
    штар
    0.45
    美術
    0.44
    лып
    0.44
    esthetics
    0.44
    ika
    0.44
    Activations Density 0.000%

    No Known Activations