© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6278
    Prev
    Next
    INDEX
    Explanations

    exploring how to develop

    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
    肩
    1.18
    通勤
    1.08
     unaccompanied
    1.04
    己
    1.04
    楠
    1.03
     Vienne
    1.03
    我が
    1.02
     Lein
    1.01
     cumprimento
    1.01
     Voluntary
    1.01
    POSITIVE LOGITS
     tìm
    1.30
     ป
    1.29
     figuring
    1.26
     analysing
    1.16
     analyzing
    1.14
    assign
    1.13
     melihat
    1.11
     analyse
    1.10
     extracting
    1.10
     mapping
    1.09
    Activations Density 0.125%

    No Known Activations