© 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. 105806
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    Criminal prosecution, jail time, frostbite

    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
    )
    0.45
     plumbers
    0.44
    🟧
    0.43
    क्यूमेंट
    0.43
     architet
    0.42
     død
    0.42
    RNAs
    0.42
    ﻯ
    0.42
     overboard
    0.41
    зонта
    0.41
    POSITIVE LOGITS
    ettle
    0.55
     जागरण
    0.53
    每一
    0.47
    ettu
    0.46
     जश्न
    0.46
     நிலையம்
    0.45
    etak
    0.45
     جشن
    0.45
     bandas
    0.45
     دلار
    0.44
    Activations Density 0.001%

    No Known Activations