© 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. 182333
    Prev
    Next
    INDEX
    Explanations

    years of have also and

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

    privacy and sharing

    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
    Чтобы
    0.53
    伊藤
    0.48
    К
    0.47
    艾
    0.46
     decrees
    0.44
     shavings
    0.43
    ServiceGroupID
    0.43
    两
    0.43
    Ꮠ
    0.43
    힐
    0.43
    POSITIVE LOGITS
     riječ
    0.45
    um
    0.45
     ceramics
    0.44
    ús
    0.43
    łów
    0.42
     weiß
    0.42
     unsolved
    0.42
     મેળ
    0.41
    ľ
    0.41
    iss
    0.41
    Activations Density 0.000%

    No Known Activations