© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13932
    Prev
    Next
    INDEX
    Explanations

    ranges and code indices

    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
     Beyonce
    0.88
     bumped
    0.88
    द्धाल
    0.88
     gripping
    0.88
    <unused1707>
    0.86
    tableView
    0.85
    गरण
    0.85
     Beyoncé
    0.85
     galle
    0.85
    艋
    0.84
    POSITIVE LOGITS
     jiné
    0.66
     Ferien
    0.62
    ভাগের
    0.56
    en
    0.56
    hower
    0.56
    She
    0.56
     Time
    0.55
     Sch
    0.55
     Zeitraum
    0.55
    7
    0.54
    Activations Density 0.078%

    No Known Activations