© 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. 150331
    Prev
    Next
    INDEX
    Explanations

    actions followed by context

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

    before the

    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
    ताल
    0.47
    డ్డ
    0.46
    ⛹
    0.46
    manha
    0.44
     활
    0.44
    🌦
    0.44
    학년
    0.43
    활
    0.43
    ⛷
    0.43
    desktop
    0.43
    POSITIVE LOGITS
     z
    0.47
     FBI
    0.45
     li
    0.45
     samt
    0.45
     Fuji
    0.44
     two
    0.44
     boric
    0.43
     Bosnian
    0.43
     for
    0.43
     worms
    0.43
    Activations Density 0.001%

    No Known Activations