© 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. 58665
    Prev
    Next
    INDEX
    Explanations

    cells with quotation marks

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

    programming variables

    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
    撻
    0.43
    罗马
    0.42
    ตลาด
    0.42
     بنابراین
    0.42
    этому
    0.41
    urato
    0.40
    ಿಸಿಕೊಂಡ
    0.40
    ದ
    0.40
    puede
    0.40
     เยอะ
    0.40
    POSITIVE LOGITS
     pillow
    0.43
     mainframe
    0.42
     you
    0.42
    *=
    0.42
     cloro
    0.41
    L
    0.39
     crows
    0.38
     zombie
    0.38
     elt
    0.38
     carne
    0.37
    Activations Density 0.000%

    No Known Activations