© 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. 97296
    Prev
    Next
    INDEX
    Explanations

    digitally remastered

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

    game protocols

    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
     advantages
    0.49
     αριθ
    0.48
     chairman
    0.48
     éch
    0.47
     derail
    0.47
     City
    0.46
     implementation
    0.46
    꽤
    0.46
     ECA
    0.46
     convinced
    0.45
    POSITIVE LOGITS
    ynchronously
    0.48
    giveness
    0.46
     каждо
    0.46
    than
    0.46
    rey
    0.45
    stro
    0.44
    плей
    0.44
    过来的
    0.44
    loved
    0.43
    noduch
    0.43
    Activations Density 0.001%

    No Known Activations