© 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. 175649
    Prev
    Next
    INDEX
    Explanations

    obligation roof inspection

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

    side of triangle or corner

    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
    Choose
    0.52
    Choosing
    0.50
    MethodBeat
    0.48
    (
    0.48
    choose
    0.47
    (?:
    0.45
    -]+
    0.43
    Combining
    0.42
    +\
    0.42
    น่า
    0.41
    POSITIVE LOGITS
     ત્રણ
    0.54
     切り
    0.54
     lanza
    0.53
     shrine
    0.52
     삼각형
    0.50
     finito
    0.49
     இரண்டு
    0.49
     രണ്ടു
    0.48
     PLAYER
    0.48
     shaker
    0.48
    Activations Density 0.002%

    No Known Activations