© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3657
    Prev
    Next
    INDEX
    Explanations

    Brasov, basmati, wisely, raspy, crisp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    yh
    1.83
    esai
    1.81
    raquinone
    1.78
    ismatch
    1.75
    uffles
    1.73
    ₓ
    1.71
    apj
    1.70
    êts
    1.69
    cción
    1.68
    ⒉
    1.66
    POSITIVE LOGITS
    cellaneous
    1.83
    htub
    1.66
    stechnik
    1.65
    hton
    1.54
    hto
    1.53
    SER
    1.53
    hev
    1.52
    exual
    1.52
    HLIGHT
    1.50
    sembly
    1.50
    Activations Density 0.301%

    No Known Activations