© 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. 56953
    Prev
    Next
    INDEX
    Explanations

    code syntax characters

    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
    argmin
    0.43
     Example
    0.42
    loadImage
    0.42
    glColor
    0.42
     columnspan
    0.41
    ``
    0.41
     other
    0.40
     이번
    0.40
    ional
    0.40
     Using
    0.39
    POSITIVE LOGITS
    酺
    0.43
     arrondie
    0.40
    قطع
    0.40
     kıs
    0.38
     vaiht
    0.37
     divino
    0.37
    eben
    0.36
     stør
    0.36
     memahami
    0.36
    шенко
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.