© 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. 8198
    Prev
    Next
    INDEX
    Explanations

    self- followed by a descriptor

    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
    бло
    0.91
    Few
    0.88
    few
    0.88
     অনেকে
    0.87
    Coins
    0.86
    Anything
    0.85
    Pts
    0.84
    ～～
    0.84
    くて
    0.84
    からない
    0.84
    POSITIVE LOGITS
     career
    1.16
     back
    0.97
     carriera
    0.96
     just
    0.95
     Karriere
    0.95
    Vere
    0.92
    career
    0.90
    usste
    0.89
     carrière
    0.89
     backward
    0.89
    Activations Density 0.077%

    No Known Activations