© 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. 11547
    Prev
    Next
    INDEX
    Explanations

    evolution of

    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
     punten
    2.84
    รางวัล
    2.70
    punten
    2.66
    亚博
    2.47
    δ
    2.41
     puntos
    2.40
    ・・
    2.36
    ังสือ
    2.35
    份额
    2.34
    faat
    2.34
    POSITIVE LOGITS
    lois
    2.92
     Small
    2.55
    sberg
    2.47
    );\
    2.45
     dey
    2.41
    ‬‬
    2.34
     randomIndex
    2.33
    )(=
    2.32
    爍
    2.30
    رش
    2.30
    Activations Density 0.014%

    No Known Activations