© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3670
    Prev
    Next
    INDEX
    Explanations

    various techniques

    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
    সাথে
    2.69
    yesha
    2.51
    ื่อน
    2.41
    ት
    2.39
    iddhi
    2.34
    حه
    2.34
     \
    2.33
    imbus
    2.33
    YO
    2.30
    て
    2.28
    POSITIVE LOGITS
    VCTargetsPath
    3.10
    েই
    2.78
    вни
    2.62
     afirmar
    2.61
    ಸ್ತು
    2.61
    undur
    2.60
     ज़रूरत
    2.59
    ӟ
    2.59
    쭤
    2.58
    un
    2.57
    Activations Density 0.113%

    No Known Activations