© 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. 242250
    Prev
    Next
    INDEX
    Explanations

    plays, executes, catalyzes

    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
    ID
    0.47
    INER
    0.46
    ;<
    0.45
    ತಾ
    0.45
    ead
    0.44
    (+)
    0.44
    ަތ
    0.44
    ᱖
    0.44
    gles
    0.43
    +$
    0.43
    POSITIVE LOGITS
     Plays
    0.57
     était
    0.55
     executes
    0.54
     zorgt
    0.54
     heeft
    0.53
     estava
    0.52
     catalyzes
    0.52
    时代
    0.51
     professionnelle
    0.50
     plays
    0.50
    Activations Density 0.000%

    No Known Activations