© 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. 152301
    Prev
    Next
    INDEX
    Explanations

    any venue

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

    remember, confidence

    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
     Tage
    0.52
    तून
    0.49
     onde
    0.48
    ع
    0.48
     Hydraul
    0.48
    న్ని
    0.48
     outliers
    0.47
    чной
    0.47
    ные
    0.47
     spaw
    0.47
    POSITIVE LOGITS
    ros
    0.53
    confidence
    0.45
    aard
    0.44
    argument
    0.43
    ítom
    0.43
    ave
    0.42
    뵙
    0.42
    casted
    0.42
    archive
    0.42
    ishan
    0.42
    Activations Density 0.000%

    No Known Activations