© 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. 7471
    Prev
    Next
    INDEX
    Explanations

    equations and variables

    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
     在
    1.18
     …
    1.15
     ，
    1.11
     为
    1.10
     前
    1.08
     Unlike
    1.07
     的
    1.06
     に
    1.06
     ...
    1.05
     impar
    1.05
    POSITIVE LOGITS
    awati
    0.89
    pertensive
    0.86
    #######
    0.82
    endela
    0.80
    dz
    0.79
     аутохтони
    0.78
    
    0.78
    ihara
    0.78
    alaikumsalam
    0.78
    szág
    0.78
    Activations Density 0.026%

    No Known Activations