© 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. 3726
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    原始内容存档
    3.08
    原始内容存档于
    2.78
    轅
    2.77
    绎
    2.72
    staking
    2.72
    ាញ
    2.63
    ették
    2.63
    dinitro
    2.61
    tender
    2.60
    publicKey
    2.59
    POSITIVE LOGITS
    روس
    3.35
    י
    3.01
    er
    2.87
    erden
    2.78
    erde
    2.74
    cane
    2.73
    ه
    2.67
    isert
    2.59
    anın
    2.57
    h
    2.50
    Activations Density 0.047%

    No Known Activations