© 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. 53419
    Prev
    Next
    INDEX
    Explanations

    financial amounts or quantities

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

    common phrases or code constructs

    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
    τ
    0.46
    chemical
    0.44
    ℤ
    0.44
     দিল্লির
    0.44
    χ
    0.43
    ཥ
    0.43
    weeks
    0.43
     化学
    0.43
    コイル
    0.42
    precision
    0.41
    POSITIVE LOGITS
    䚰
    0.50
    .??
    0.45
     blotting
    0.43
    他不
    0.43
     عن
    0.43
     resurgence
    0.43
     shrinking
    0.42
     මැ
    0.42
    .).
    0.42
    誢
    0.42
    Activations Density 0.000%

    No Known Activations