© 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. 60504
    Prev
    Next
    INDEX
    Explanations

    chosen you

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

    terminal followed by website or colon

    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
    ALBERT
    0.51
    Art
    0.51
    -}\
    0.48
    para
    0.45
    ART
    0.44
    ivan
    0.44
    AL
    0.43
    maximal
    0.43
    ELL
    0.43
    ARIA
    0.42
    POSITIVE LOGITS
    я
    0.58
    ة
    0.50
    ໍາ
    0.49
     Manipur
    0.48
    τα
    0.46
     încep
    0.46
    ि
    0.46
    ні
    0.46
     Ř
    0.46
     regulate
    0.45
    Activations Density 0.000%

    No Known Activations