© 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. 99037
    Prev
    Next
    INDEX
    Explanations

    conventions and investing

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

    Python libraries and technical terms

    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
    낭
    0.51
    老婆
    0.48
     뭐야
    0.48
    ኖ
    0.48
     Queer
    0.48
     Ведь
    0.47
     Tolkien
    0.46
     क्वेश्च
    0.46
    ಂಭ
    0.46
     अभिनय
    0.45
    POSITIVE LOGITS
    forms
    0.57
    tan
    0.56
    -
    0.52
    t
    0.52
    St
    0.50
    :
    0.50
    stig
    0.50
    dv
    0.50
    ,
    0.50
    printf
    0.49
    Activations Density 0.000%

    No Known Activations