© 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. 33704
    Prev
    Next
    INDEX
    Explanations

    award-winning informative discussions

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

    suffering, humanity, crime, self, heap, application, exit

    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
     gameState
    0.47
     Flücht
    0.45
    െയി
    0.45
     isn
    0.44
    힌
    0.44
     alternativas
    0.43
     রাজ্য
    0.43
     AlertDialog
    0.43
    jati
    0.42
    ាំ
    0.42
    POSITIVE LOGITS
    ixon
    0.50
    -------*/
    0.48
    /(
    0.47
    纜
    0.46
    (/(
    0.46
    θεση
    0.45
    เทพ
    0.45
    -【
    0.45
     تب
    0.45
    zim
    0.45
    Activations Density 0.000%

    No Known Activations