© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2261
    Prev
    Next
    INDEX
    Explanations

    team context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     U
    1.76
     sh
    1.73
     sym
    1.71
     terrible
    1.71
     subtle
    1.68
     awkward
    1.67
    U
    1.63
     exception
    1.62
     consequence
    1.62
     course
    1.61
    POSITIVE LOGITS
    旗下
    2.86
     ponú
    2.85
     adaptés
    2.82
     rotacao
    2.77
    webElementXpaths
    2.74
    봤
    2.69
     cuentan
    2.66
     coseno
    2.66
     dejaron
    2.64
     avanzados
    2.60
    Activations Density 0.003%

    No Known Activations