© 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. 12487
    Prev
    Next
    INDEX
    Explanations

    knife and cutting tools

    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
    اً
    3.69
    ا
    3.34
    lg
    2.94
    tted
    2.74
    semer
    2.73
    rd
    2.61
    了
    2.60
    اا
    2.56
    th
    2.52
    ূর্ণ
    2.52
    POSITIVE LOGITS
    FirstResponder
    2.79
    ↵
    2.79
    ikation
    2.73
    йон
    2.72
    iffent
    2.64
    Curso
    2.64
    igham
    2.63
    関連項目
    2.58
     lecteur
    2.57
     renewed
    2.57
    Activations Density 0.015%

    No Known Activations