© 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. 62099
    Prev
    Next
    INDEX
    Explanations

    legal thresholds

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

    self-defense

    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
     conting
    0.43
     pension
    0.41
    가가
    0.41
    夫人
    0.40
    })$,
    0.40
     expos
    0.39
     truckers
    0.39
    ackbar
    0.38
     SKAction
    0.38
    κα
    0.38
    POSITIVE LOGITS
    Threshold
    0.49
     thresholds
    0.47
     threshold
    0.47
     merak
    0.46
    ftl
    0.45
    THRESHOLD
    0.45
     Threshold
    0.45
    tbl
    0.45
     ഓ
    0.44
     xhr
    0.43
    Activations Density 0.013%

    No Known Activations