© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2385
    Prev
    Next
    INDEX
    Explanations

    death and old things

    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
    ي
    2.68
    accio
    2.31
    AC
    2.27
    ac
    2.27
    च
    2.19
    কেট
    2.11
    kjhtml
    2.07
    ্টা
    2.06
     নির্যা
    2.04
    ृत
    2.01
    POSITIVE LOGITS
     resting
    2.41
     --------------
    2.41
     ---------------
    2.37
    een
    2.26
     -------------
    2.25
    گیا
    2.20
     នៅ
    2.19
    ুণ
    2.18
    ందరు
    2.17
    ശി
    2.17
    Activations Density 0.239%

    No Known Activations