© 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. 113323
    Prev
    Next
    INDEX
    Explanations

    listing items or actions

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

    stage rockets

    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
     sandpaper
    0.50
    oui
    0.47
     outils
    0.46
     vivido
    0.45
     ISSUE
    0.44
     factors
    0.44
     sakit
    0.44
    겟
    0.44
     raids
    0.44
     scriptures
    0.44
    POSITIVE LOGITS
     之
    0.49
     場
    0.48
    を追加
    0.48
     тү
    0.48
    АО
    0.48
     版
    0.47
     Ту
    0.46
     群
    0.46
    ఎఫ్
    0.46
     ску
    0.45
    Activations Density 0.002%

    No Known Activations