© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14945
    Prev
    Next
    INDEX
    Explanations

    commands

    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_13_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
     компании
    1.89
    Accom
    1.85
     построен
    1.76
    Aqu
    1.73
    Sub
    1.71
    Pun
    1.65
    ⏩
    1.64
    Компания
    1.64
    Brick
    1.64
    anges
    1.64
    POSITIVE LOGITS
    י
    1.73
    orderBy
    1.52
    a
    1.42
    루
    1.35
    ی
    1.35
     average
    1.33
    ל
    1.32
    iensis
    1.32
    𝙜
    1.31
    ీ
    1.31
    Activations Density 0.001%

    No Known Activations