© 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. 116959
    Prev
    Next
    INDEX
    Explanations

    how do

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

    merging, franchising, cycles, dosage, synergizing

    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
     Z
    0.61
     Zombie
    0.50
     Chaplain
    0.50
     Czar
    0.50
     الز
    0.49
     جاس
    0.49
     Emile
    0.48
     Hormone
    0.48
     ז
    0.47
     मिळू
    0.47
    POSITIVE LOGITS
     требованиям
    0.50
    government
    0.48
    合い
    0.48
    必要な
    0.46
    зиден
    0.45
    હેરા
    0.45
     obtención
    0.44
    бет
    0.44
    ัต
    0.44
    зульта
    0.44
    Activations Density 0.000%

    No Known Activations