© 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. 18182
    Prev
    Next
    INDEX
    Explanations

    rather than

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

    contrasting focus

    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
    3
    0.81
    4
    0.70
    6
    0.63
    5
    0.63
    IGHT
    0.62
     Veterans
    0.62
     Thermodynamics
    0.61
    1
    0.59
    ähr
    0.59
    8
    0.59
    POSITIVE LOGITS
    er
    0.71
    ти
    0.61
    erode
    0.61
    in
    0.61
    ુ
    0.60
    ان
    0.57
    あくまで
    0.57
    ার
    0.56
    な
    0.55
    ir
    0.54
    Activations Density 0.016%

    No Known Activations