© 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. 77352
    Prev
    Next
    INDEX
    Explanations

    royal Harry citrus magazine

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

    like these

    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
    -
    0.56
    -(\
    0.53
     bemo
    0.49
    (?
    0.49
    ){
    0.48
    als
    0.48
    ?)
    0.47
    ally
    0.47
    !(
    0.46
    (
    0.46
    POSITIVE LOGITS
     тільки
    0.49
     Evaluación
    0.47
     seguire
    0.46
     There
    0.45
     zvlá
    0.45
     réponse
    0.45
     résult
    0.45
     слід
    0.45
     FOLLOW
    0.45
     Segu
    0.45
    Activations Density 0.000%

    No Known Activations