© 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. 105441
    Prev
    Next
    INDEX
    Explanations

    how and fact patterns

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

    asking how something functions

    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
    un
    0.57
    ni
    0.50
    an
    0.49
    in
    0.47
    es
    0.47
    怦
    0.46
    o
    0.45
    льм
    0.45
    ikiran
    0.45
     echoing
    0.44
    POSITIVE LOGITS
    埃
    0.48
     IAU
    0.47
    ｝
    0.45
    袁
    0.44
    ។
    0.44
    デル
    0.43
    ラス
    0.42
     அவற்றை
    0.42
    」（
    0.42
    간다
    0.42
    Activations Density 0.001%

    No Known Activations