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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 584
    Prev
    Next
    INDEX
    Explanations

    numbers and amounts

    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
     വ്യക്ത
    0.92
    ස්ථ
    0.90
    拿下
    0.83
     الثالثه
    0.82
    赟
    0.81
     épaules
    0.80
     îi
    0.79
    ؛
    0.79
     allá
    0.79
     بالنسبه
    0.79
    POSITIVE LOGITS
     thousand
    2.41
    thousand
    2.15
     million
    2.14
     thousands
    1.96
    million
    1.93
     тысяч
    1.84
    万
    1.83
    thousands
    1.75
     Million
    1.72
     тыся
    1.71
    Activations Density 1.345%

    No Known Activations