© 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. 73007
    Prev
    Next
    INDEX
    Explanations

    correlation and correspondence

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

    correlation and rate of change

    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
     unbounded
    0.44
     superar
    0.44
    グループ
    0.43
    團
    0.43
    odhya
    0.42
     worst
    0.41
     सीमाओं
    0.41
     definir
    0.41
    团
    0.41
    BINARY
    0.41
    POSITIVE LOGITS
     correlating
    0.48
    correlated
    0.46
     correlated
    0.43
     plotting
    0.43
    对应的
    0.43
     correlation
    0.42
    Correlation
    0.42
     corresponding
    0.42
    plotting
    0.42
     Correlation
    0.40
    Activations Density 0.009%

    No Known Activations