© 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. 8067
    Prev
    Next
    INDEX
    Explanations

    speech quotes punctuation

    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
     context
    1.09
     egreg
    1.04
     contexte
    1.02
    fer
    1.00
    وید
    0.97
     contexts
    0.96
     effector
    0.94
     ἔ
    0.92
     incoming
    0.92
    executor
    0.91
    POSITIVE LOGITS
    Kalau
    1.43
    ানুভূতি
    1.42
    hitth
    1.42
     "))
    1.40
    <unused1632>
    1.39
     Kuala
    1.38
    aurait
    1.38
    %">
    1.37
    amboo
    1.35
     Tetapi
    1.32
    Activations Density 0.000%

    No Known Activations