© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4473
    Prev
    Next
    INDEX
    Explanations

    version control and build commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Barrios
    1.75
     Rollins
    1.57
    ights
    1.52
     Kamb
    1.51
    hia
    1.48
    igur
    1.46
    šit
    1.41
    /=
    1.41
    iul
    1.40
     headless
    1.39
    POSITIVE LOGITS
    datei
    1.44
     science
    1.23
     ciência
    1.22
    SCIENCE
    1.20
    ریشن
    1.19
    јединачна
    1.19
    Science
    1.19
    진
    1.18
    odynamic
    1.18
    ENER
    1.16
    Activations Density 0.081%

    No Known Activations