© 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. 83480
    Prev
    Next
    INDEX
    Explanations

    legal and administrative terms

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

    key terms followed by colon

    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
     statements
    0.50
     liters
    0.47
     standardize
    0.46
     guesses
    0.46
    ст
    0.45
     $-
    0.45
    샥
    0.45
     verschillende
    0.44
     simbol
    0.44
     physiological
    0.44
    POSITIVE LOGITS
     Etat
    0.49
     Executors
    0.49
     ترا
    0.45
     Mitte
    0.45
     Treasures
    0.44
     Cultures
    0.44
     Alumni
    0.43
     Á
    0.43
    ioners
    0.43
     وكان
    0.42
    Activations Density 0.001%

    No Known Activations