© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10517
    Prev
    Next
    INDEX
    Explanations

    ตามเวลา ปกติ ไปด้วย

    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
    ध्ये
    2.78
    amt
    2.59
    )|$(
    2.58
    炬
    2.52
    ല്ലാം
    2.49
     courant
    2.48
    รรม
    2.47
    fragen
    2.47
    izont
    2.43
    iexpress
    2.42
    POSITIVE LOGITS
    rí
    2.53
    Ꮯ
    2.50
    InputElement
    2.38
    zj
    2.37
    <!
    2.36
    KEYDOWN
    2.36
    కి
    2.36
     onc
    2.35
    bare
    2.34
    ••••
    2.34
    Activations Density 0.003%

    No Known Activations