© 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. 59866
    Prev
    Next
    INDEX
    Explanations

    County Sheriff, Justice

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

    New York loans

    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
     redesignated
    0.44
     amalgamated
    0.44
     ఏద
    0.44
    弃
    0.43
     DHT
    0.43
     demonstrated
    0.43
     about
    0.42
     Ablauf
    0.42
     образова
    0.42
     entender
    0.42
    POSITIVE LOGITS
    ურთიერთ
    0.49
    Ин
    0.48
    Rosen
    0.47
    ações
    0.47
    RECENT
    0.47
    Adap
    0.47
    }}.
    0.46
    cans
    0.46
    कॉइन
    0.46
    WALL
    0.45
    Activations Density 0.000%

    No Known Activations