© 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. 114607
    Prev
    Next
    INDEX
    Explanations

    bouts, stints, trials, costs

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

    blood sugar swings and oscillations

    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
    에게
    0.51
     ตาย
    0.51
    𝕟
    0.50
    fur
    0.50
    ~.,
    0.49
    劍
    0.48
    졍
    0.47
     Gebäude
    0.46
    農
    0.46
    نتي
    0.46
    POSITIVE LOGITS
     bouts
    0.52
     moieties
    0.51
    errick
    0.50
     trims
    0.50
    tests
    0.50
     trim
    0.49
     stints
    0.49
     oscillations
    0.48
     trials
    0.46
     moods
    0.46
    Activations Density 0.000%

    No Known Activations