© 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. 191902
    Prev
    Next
    INDEX
    Explanations

    more flavorful

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

    harmful chemicals and impure products

    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
     Grease
    0.45
    Become
    0.45
     drab
    0.45
    viat
    0.44
     ગે
    0.44
    ཝ
    0.43
    clickHandler
    0.42
    graded
    0.42
    աք
    0.42
     دوا
    0.42
    POSITIVE LOGITS
    Excluded
    0.56
    J
    0.48
    N
    0.48
     মুক্ত
    0.48
    iyi
    0.47
    mk
    0.45
    F
    0.45
    AND
    0.45
    nn
    0.45
    IL
    0.44
    Activations Density 0.000%

    No Known Activations