© 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. 8133
    Prev
    Next
    INDEX
    Explanations

    layered narrative possibilities

    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
    t
    1.54
    க
    1.48
    tl
    1.47
    tam
    1.38
    g
    1.29
    s
    1.26
    tte
    1.26
    gm
    1.25
    duled
    1.25
    tf
    1.25
    POSITIVE LOGITS
    デア
    1.33
    榉
    1.17
    玮
    1.10
    ὰ
    1.09
    喏
    1.07
     darkness
    1.07
     conteúdos
    1.06
    ズム
    1.06
    宙
    1.06
    URF
    1.04
    Activations Density 0.000%

    No Known Activations