© 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. 49319
    Prev
    Next
    INDEX
    Explanations

    office, identity, grateful, winning, other, written, always

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

    Java dependency injection

    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
    >
    0.52
    ‘
    0.49
    0.47
    enl
    0.46
    <b>
    0.45
    *
    0.45
    {
    0.42
    elev
    0.41
    <strong>
    0.41
    ↵↵
    0.40
    POSITIVE LOGITS
     haies
    0.47
     pihak
    0.46
     prilikom
    0.45
     fría
    0.44
     mahdoll
    0.44
     griega
    0.44
     kemungkinan
    0.44
     nedeniyle
    0.43
     recorder
    0.43
     portuguesa
    0.43
    Activations Density 0.000%

    No Known Activations