© 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. 8216
    Prev
    Next
    INDEX
    Explanations

    making a copy

    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
    ()
    1.47
    ())
    1.38
    ()),
    1.24
    ());
    1.21
    ().
    1.21
    ();
    1.19
    ()->
    1.19
    ()]
    1.18
    ()==
    1.17
    (){
    1.17
    POSITIVE LOGITS
     Fancy
    0.97
     మరో
    0.87
     تانيه
    0.84
     selv
    0.82
     dvě
    0.81
     दुसरी
    0.79
    WIT
    0.79
     augmented
    0.78
    plus
    0.78
    Fancy
    0.77
    Activations Density 0.024%

    No Known Activations