© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1996
    Prev
    Next
    INDEX
    Explanations

    sequential actions or steps

    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_13_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
    ile
    2.08
    ング
    1.75
    p
    1.74
    ism
    1.69
    ither
    1.68
     अनुसार
    1.60
     dis
    1.55
    ve
    1.54
    hem
    1.54
     exh
    1.53
    POSITIVE LOGITS
    <unused878>
    2.41
    <unused846>
    2.41
    𒄐
    2.39
    <unused786>
    2.38
    LOTREntity
    2.35
    <unused873>
    2.34
    <unused965>
    2.34
     言っ
    2.30
    <unused751>
    2.30
    <unused1693>
    2.30
    Activations Density 0.764%

    No Known Activations