© 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. 49674
    Prev
    Next
    INDEX
    Explanations

    causes of problems

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

    configuration code artifacts

    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
    魯
    0.45
    गा
    0.45
    फै
    0.44
    edent
    0.44
    בין
    0.43
    unities
    0.42
    assies
    0.42
    را
    0.42
    enaar
    0.41
    ״
    0.41
    POSITIVE LOGITS
     investigation
    0.53
     concealment
    0.53
     display
    0.51
     investigative
    0.49
     detection
    0.48
     optimization
    0.48
     examiners
    0.48
     bereavement
    0.48
     examination
    0.47
     Reveal
    0.47
    Activations Density 0.000%

    No Known Activations