© 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. 15204
    Prev
    Next
    INDEX
    Explanations

    describing what is involved

    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
    ︎
    1.78
    াইলেন
    1.65
    atically
    1.42
    ႇ
    1.37
    erler
    1.32
    ступает
    1.27
     trick
    1.26
    Overall
    1.25
    াইজ
    1.25
    верну
    1.23
    POSITIVE LOGITS
    bfs
    1.50
    ност
    1.44
    坻
    1.39
    Muito
    1.37
    ścia
    1.35
    ści
    1.35
    mité
    1.31
     setContentView
    1.28
    நே
    1.28
     مطالعه
    1.28
    Activations Density 0.055%

    No Known Activations