© 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. 12320
    Prev
    Next
    INDEX
    Explanations

    Log, ORD, quick, Prompt

    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
     کرام
    3.35
    ÷
    2.67
    wenn
    2.60
     höch
    2.54
    ্ম্ম
    2.45
    ufer
    2.44
    ்சை
    2.41
    itteln
    2.37
    瘤
    2.34
    لال
    2.34
    POSITIVE LOGITS
    𝐨
    2.79
    ly
    2.78
    𝐞
    2.75
    stock
    2.57
    prises
    2.56
    sor
    2.55
    sg
    2.53
    ками
    2.53
    𝐟
    2.52
    ところで
    2.52
    Activations Density 0.004%

    No Known Activations