© 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. 8300
    Prev
    Next
    INDEX
    Explanations

    twirling, autonomy, twelve, Twitch

    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
    대한
    1.01
     대한
    0.90
    দ্য
    0.88
    ச்சூழ
    0.87
     boule
    0.86
     슬
    0.85
    ಮೆ
    0.85
    绍
    0.85
     instinct
    0.84
     बरे
    0.83
    POSITIVE LOGITS
    elve
    1.33
    ENTY
    1.17
    ilight
    1.15
    elfth
    1.12
    inned
    1.10
    isters
    1.09
    entieth
    1.08
    isting
    1.06
    itters
    1.05
    isted
    1.03
    Activations Density 0.024%

    No Known Activations