© 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. 54582
    Prev
    Next
    INDEX
    Explanations

    legal claims or consent

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

    information and definitions

    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
    闲
    0.48
    苍
    0.47
    스가
    0.46
    mone
    0.45
    侦
    0.45
    tolerance
    0.43
    蒼
    0.43
    也没
    0.43
    Tolerance
    0.43
    恃
    0.42
    POSITIVE LOGITS
     recipe
    0.54
     §§
    0.54
     can
    0.50
     pushbutton
    0.49
     pushing
    0.49
     subparagraph
    0.47
    »،
    0.47
     atmospheric
    0.47
     academia
    0.46
     section
    0.46
    Activations Density 0.000%

    No Known Activations