© 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. 11146
    Prev
    Next
    INDEX
    Explanations

    birds fly high, Keaton, amino acid, Crane

    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
    ‌
    2.55
    ند
    2.55
     ri
    2.54
    ⓧ
    2.43
    נטי
    2.41
    ri
    2.39
    өм
    2.35
     seg
    2.31
    짙
    2.25
    נה
    2.24
    POSITIVE LOGITS
    तावनी
    3.56
    erden
    3.47
    ୍
    3.29
    dling
    3.22
    丷
    3.21
    erver
    3.13
    dler
    3.12
    OURCE
    3.05
    nade
    3.00
     Helv
    2.94
    Activations Density 0.004%

    No Known Activations