© 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. 151052
    Prev
    Next
    INDEX
    Explanations

    label, manner, biscuits, short

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

    incredibly complex

    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
    Slf
    0.53
    needed
    0.50
    grond
    0.48
     혹은
    0.47
    ¹.
    0.46
    ổng
    0.44
     또는
    0.44
     grond
    0.43
    _|
    0.43
     અથ
    0.43
    POSITIVE LOGITS
     complications
    0.50
     excursions
    0.50
    ће
    0.49
     Mechanics
    0.48
     изобра
    0.48
     поез
    0.48
     Vis
    0.47
     fiestas
    0.45
    чә
    0.45
     complicaciones
    0.45
    Activations Density 0.001%

    No Known Activations