© 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. 59433
    Prev
    Next
    INDEX
    Explanations

    Free, Get, Hold, Behind, You, Generally

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

    political, military, historical, territorial actions

    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
    බ
    0.41
     Lego
    0.39
    ワー
    0.39
     Calvert
    0.38
     mudd
    0.38
    铡
    0.38
     Locust
    0.38
    워크
    0.37
     Midi
    0.37
     slap
    0.36
    POSITIVE LOGITS
    pèce
    0.47
    perties
    0.44
     परिवेश
    0.43
    entity
    0.41
    葆
    0.41
     क्षेत्रा
    0.41
    chés
    0.40
    integrity
    0.40
    稔
    0.40
     THAT
    0.40
    Activations Density 0.001%

    No Known Activations