© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11335
    Prev
    Next
    INDEX
    Explanations

    boxed answers

    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_13_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
     자랑
    1.17
     பிரசா
    1.11
    atche
    1.07
     Distrito
    1.06
    medal
    1.05
    новні
    1.05
    很大
    1.04
    晉
    1.03
    obviously
    1.03
    વાન
    1.02
    POSITIVE LOGITS
     frustration
    1.12
     frust
    1.08
     scriv
    1.03
     hatred
    1.00
     depressive
    0.98
     hateful
    0.97
     entrop
    0.93
     frustrations
    0.93
     pessimism
    0.92
     discordant
    0.91
    Activations Density 0.168%

    No Known Activations