© 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. 10542
    Prev
    Next
    INDEX
    Explanations

    what it is

    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
     휘
    3.05
    ი
    2.71
    ುದು
    2.62
    ווי
    2.60
    inud
    2.58
    고
    2.48
    ikation
    2.46
    sam
    2.46
    인더
    2.44
    芏
    2.40
    POSITIVE LOGITS
    āti
    2.69
    uparavant
    2.67
     flushed
    2.56
    వరకు
    2.55
     foremost
    2.50
    hetically
    2.50
    ariamente
    2.49
    াতাড়ি
    2.48
    isiert
    2.41
    ótes
    2.41
    Activations Density 0.020%

    No Known Activations