© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7893
    Prev
    Next
    INDEX
    Explanations

    preparation verbs

    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_22_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
    án
    0.75
     fins
    0.71
    みました
    0.71
    די
    0.69
    볶
    0.69
    цене
    0.69
    輸入品
    0.69
    ස්
    0.68
    Ả
    0.67
    umas
    0.67
    POSITIVE LOGITS
     ik
    0.86
     noved
    0.76
     इक
    0.76
     Miguel
    0.75
    imia
    0.74
     सार्थक
    0.74
    近代
    0.73
     тот
    0.72
     aquel
    0.72
     quelle
    0.72
    Activations Density 0.059%

    No Known Activations