© 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. 210972
    Prev
    Next
    INDEX
    Explanations

    addressed Home Plans

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

    about why not

    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
     是否
    0.61
     嗯
    0.59
     少し
    0.55
     單
    0.55
     감소
    0.55
     również
    0.54
     Filament
    0.53
     brunâtre
    0.53
     समुदा
    0.53
     Также
    0.52
    POSITIVE LOGITS
    rijk
    0.51
    that
    0.50
     spatial
    0.50
     You
    0.48
    concentration
    0.46
     mathematical
    0.45
    You
    0.45
    eig
    0.44
    out
    0.44
    *
    0.44
    Activations Density 0.000%

    No Known Activations