© 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. 145715
    Prev
    Next
    INDEX
    Explanations

    invoice discounting

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

    value, information, and relationships

    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
    0.56
     there
    0.49
    %
    0.45
    //
    0.45
    www
    0.44
    member
    0.43
    there
    0.43
    \\
    0.42
     the
    0.42
    console
    0.42
    POSITIVE LOGITS
     sicuramente
    0.50
     وإ
    0.49
     razon
    0.48
    AutoStabilise
    0.47
     পদার্থ
    0.46
     aquello
    0.45
    െന്നും
    0.45
     hayvan
    0.45
    纍
    0.45
     ayuda
    0.45
    Activations Density 0.000%

    No Known Activations