© 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. 97875
    Prev
    Next
    INDEX
    Explanations

    asset management

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

    non-english or symbol

    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
     t
    0.45
    r
    0.43
    orting
    0.42
     mell
    0.40
     cheat
    0.38
     cheats
    0.38
     newInput
    0.38
     Grayson
    0.37
    ø
    0.37
    的想法
    0.37
    POSITIVE LOGITS
    ❾
    0.48
     fonctionner
    0.47
    illerato
    0.46
    彘
    0.46
     पाहिजे
    0.46
     вигля
    0.45
    㧋
    0.44
     আসনে
    0.44
     ॥
    0.43
     постоянно
    0.43
    Activations Density 0.000%

    No Known Activations