© 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. 12140
    Prev
    Next
    INDEX
    Explanations

    HELP followed by parenthesis

    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
     Та
    1.31
     И
    1.25
    时期
    1.23
     По
    1.21
     ش
    1.20
     Ан
    1.20
    荣誉
    1.20
     Х
    1.19
     Ка
    1.19
    년
    1.18
    POSITIVE LOGITS
     skew
    1.33
     scram
    1.20
     skewed
    1.12
     steeper
    1.11
     brisk
    1.09
     marginally
    1.09
     inversely
    1.07
     wobei
    1.06
     tighter
    1.02
     gravy
    1.01
    Activations Density 0.015%

    No Known Activations