© 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. 162530
    Prev
    Next
    INDEX
    Explanations

    legal judgments and decisions

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

    demonstrate your accomplishments

    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
     조합
    0.44
     Conversely
    0.44
     incremento
    0.41
    Bechyné
    0.40
     tendon
    0.39
     ก
    0.38
    回归
    0.38
    ambulance
    0.38
    IZ
    0.37
     mower
    0.37
    POSITIVE LOGITS
     আর্
    0.42
     postmodern
    0.41
    enziali
    0.40
    Judgment
    0.40
    zigen
    0.40
    上映
    0.39
     الاعزاء
    0.39
    judgment
    0.39
    📍
    0.39
    فى
    0.39
    Activations Density 0.001%

    No Known Activations