© 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. 3687
    Prev
    Next
    INDEX
    Explanations

    cannot do

    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
     âm
    1.47
    ศ
    1.31
     tài
    1.31
     संगीत
    1.26
     مرور
    1.26
    才
    1.24
    ํ
    1.23
     Vista
    1.22
    ครับ
    1.19
     ๆ
    1.19
    POSITIVE LOGITS
    criar
    1.67
     twigs
    1.55
     cores
    1.52
     baskets
    1.50
    hota
    1.46
     batters
    1.45
     straws
    1.44
    ao
    1.42
     triangles
    1.40
    getSession
    1.40
    Activations Density 0.007%

    No Known Activations