© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14723
    Prev
    Next
    INDEX
    Explanations

    youtube videos explaining concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blown
    0.85
    ಿದರು
    0.83
    보고
    0.76
    クル
    0.76
     깊
    0.73
    항
    0.73
    гла
    0.73
    nights
    0.72
     informant
    0.71
    tip
    0.70
    POSITIVE LOGITS
     Traction
    1.17
     セ
    1.08
     Hai
    0.99
     Cer
    0.99
     Cy
    0.98
     Cis
    0.98
     Rename
    0.98
     Lose
    0.97
     Get
    0.96
     Chat
    0.96
    Activations Density 0.002%

    No Known Activations