© 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. 99337
    Prev
    Next
    INDEX
    Explanations

    Property updates component

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

    available analytics growing system signal Dental

    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
    XT
    0.47
    Terry
    0.46
    岦
    0.46
     फाउंड
    0.45
     यादगार
    0.45
    GK
    0.44
     करेक्ट
    0.44
    randn
    0.43
     Tired
    0.43
     humains
    0.43
    POSITIVE LOGITS
     finalizar
    0.45
     レ
    0.43
     secu
    0.43
    сподар
    0.43
    視
    0.43
     ブラ
    0.42
     hilo
    0.42
     longitudine
    0.42
    ᅱ
    0.42
     開
    0.42
    Activations Density 0.000%

    No Known Activations