© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 71851
    Prev
    Next
    INDEX
    Explanations

    be liable, us through

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

    listing items after category markers

    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
     AuthService
    0.46
     SINGH
    0.46
     ORIGINAL
    0.45
    SETTINGS
    0.42
    忠
    0.42
    settings
    0.42
     WebDriver
    0.42
    志
    0.42
    dH
    0.41
     ডিসেম্বর
    0.41
    POSITIVE LOGITS
     mis
    0.48
    buffalo
    0.47
    Roi
    0.46
     stalling
    0.46
    '
    0.46
    statistical
    0.44
    '...
    0.44
    atello
    0.44
    ⊔
    0.44
     статисти
    0.44
    Activations Density 0.000%

    No Known Activations