© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 910
    Prev
    Next
    INDEX
    Explanations

    overall impression

    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
    ClkInitStruct
    1.88
     pagamento
    1.76
    <unused1956>
    1.74
    ワ
    1.73
    ProjectReference
    1.71
     taux
    1.70
    ρέπει
    1.68
    畊
    1.67
    AnyCPU
    1.66
    ১২
    1.64
    POSITIVE LOGITS
    л
    1.72
    u
    1.69
    ed
    1.61
    ligence
    1.57
    iere
    1.56
    ్రే
    1.53
    lat
    1.51
    usian
    1.51
    tı
    1.49
    ్రియ
    1.49
    Activations Density 0.002%

    No Known Activations