© 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. 168225
    Prev
    Next
    INDEX
    Explanations

    quantities, supplements, options

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

    super fancy

    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
     individuality
    0.54
     spirited
    0.53
    VIA
    0.52
     o
    0.51
    STRAINT
    0.50
     USED
    0.50
     강
    0.49
     quenched
    0.48
     chloride
    0.48
     patriotism
    0.48
    POSITIVE LOGITS
    kak
    0.57
    n
    0.52
    kopf
    0.50
    etzen
    0.50
    老师
    0.49
    nina
    0.48
    ίο
    0.48
     навча
    0.47
    etl
    0.47
    ıkları
    0.46
    Activations Density 0.000%

    No Known Activations