© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8265
    Prev
    Next
    INDEX
    Explanations

    parentheses with abbreviations

    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_22_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
    W
    1.34
    L
    1.31
    H
    1.28
     F
    1.28
    F
    1.25
     C
    1.25
    D
    1.25
    N
    1.24
     H
    1.23
     W
    1.23
    POSITIVE LOGITS
     ae
    0.80
     nb
    0.75
     ea
    0.72
     भो
    0.72
     careers
    0.72
     aa
    0.71
     da
    0.71
     ka
    0.71
     fined
    0.71
    我和
    0.70
    Activations Density 0.287%

    No Known Activations