© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4903
    Prev
    Next
    INDEX
    Explanations

    provided feedback or explanations

    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
     getValue
    1.35
     colaboradores
    1.33
     防止
    1.32
     몸
    1.32
     알
    1.32
     仕事
    1.31
     ENTRE
    1.31
     Kiến
    1.26
     武
    1.26
     耐
    1.25
    POSITIVE LOGITS
     similarly
    1.46
    also
    1.41
     somewhat
    1.40
     likewise
    1.37
     forthwith
    1.37
     utterly
    1.31
     decidedly
    1.29
     emanating
    1.29
    completely
    1.29
     also
    1.28
    Activations Density 0.079%

    No Known Activations