© 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. 227167
    Prev
    Next
    INDEX
    Explanations

    chlorine dioxide, traditional cigarettes

    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
     late
    0.43
     converge
    0.43
     since
    0.43
     shovel
    0.43
    ❶
    0.43
    onomy
    0.42
     convergence
    0.42
     begin
    0.42
     magnitude
    0.42
    ukary
    0.42
    POSITIVE LOGITS
    盹
    0.44
     أم
    0.43
    沺
    0.43
    माम
    0.42
    सेना
    0.42
     પોતાના
    0.42
     Dauer
    0.42
    ث
    0.41
     Nina
    0.41
    णासाठी
    0.41
    Activations Density 0.002%

    No Known Activations