© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10963
    Prev
    Next
    INDEX
    Explanations

    focus on options

    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
    γγελμα
    0.96
    λαμβ
    0.86
     পড়ুন
    0.85
     নিরাপ
    0.85
    ͇
    0.84
     me
    0.82
    ಾರದ
    0.81
    стите
    0.79
     text
    0.79
     waffle
    0.78
    POSITIVE LOGITS
    ného
    1.22
    แอ
    1.07
    Jackson
    1.04
    यु
    1.01
     герцо
    0.99
     फो
    0.98
    ័
    0.97
    Pyrid
    0.97
    ยุ
    0.95
    унд
    0.95
    Activations Density 0.000%

    No Known Activations