© 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. 7429
    Prev
    Next
    INDEX
    Explanations

    offer help and understanding

    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
     நூ
    0.89
     agama
    0.86
     ofrec
    0.84
    вере
    0.84
    亠
    0.83
     clot
    0.83
     обна
    0.82
     desech
    0.82
    颜
    0.82
     लिखें
    0.81
    POSITIVE LOGITS
     miss
    2.18
    miss
    2.15
     misses
    1.93
     missed
    1.91
     MISS
    1.89
     Miss
    1.81
    Miss
    1.76
    MISS
    1.72
     Missing
    1.63
     missing
    1.57
    Activations Density 0.064%

    No Known Activations