© 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. 9710
    Prev
    Next
    INDEX
    Explanations

    supporting character descriptions

    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
    θεί
    1.09
    륙
    1.08
    දහ
    1.03
    氳
    0.99
    ζεται
    0.99
     kéo
    0.97
    氲
    0.96
    礴
    0.96
    isLoading
    0.95
    镛
    0.95
    POSITIVE LOGITS
     Solving
    1.11
     solving
    1.10
     Solutions
    1.00
     Solve
    0.98
    Answers
    0.96
     الحل
    0.95
     Answers
    0.95
    solutions
    0.95
     Mull
    0.94
     التمرين
    0.94
    Activations Density 0.001%

    No Known Activations