© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1016
    Prev
    Next
    INDEX
    Explanations

    offers a

    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
    ais
    1.48
    We
    1.46
    uk
    1.46
    assim
    1.40
    ron
    1.39
    bd
    1.38
    وي
    1.36
    ç
    1.35
    ्यान
    1.35
    phy
    1.34
    POSITIVE LOGITS
     ACTUAL
    1.73
    -...
    1.70
     FORMAT
    1.61
     ANYTHING
    1.60
     MAGAZ
    1.58
    }"/>
    1.57
    -​
    1.55
    -<
    1.55
     관한
    1.55
     TextAppearance
    1.55
    Activations Density 2.935%

    No Known Activations