© 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. 561
    Prev
    Next
    INDEX
    Explanations

    programming exceptions and statements

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

    code structures and declarations

    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
    ometrical
    0.37
    apatt
    0.37
    unehmen
    0.37
    allelujah
    0.37
    螓
    0.36
    rifugal
    0.36
     enfermo
    0.36
    stethoscope
    0.36
    cdot
    0.35
    attho
    0.35
    POSITIVE LOGITS
    Factory
    0.44
    ({
    0.41
    ::
    0.38
     created
    0.38
     create
    0.37
     proveedores
    0.37
     {
    0.36
     With
    0.36
     provider
    0.36
     politician
    0.36
    Activations Density 0.012%

    No Known Activations