© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1863
    Prev
    Next
    INDEX
    Explanations

    explaining difficulty or how to do something

    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_13_width_65k_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
    ダー
    1.03
    oleč
    0.98
    庤
    0.95
    編
    0.95
     también
    0.94
    တယ်
    0.94
     カ
    0.94
    也有
    0.94
     கண்கா
    0.93
     کردیا
    0.93
    POSITIVE LOGITS
     anymore
    2.00
     nor
    1.58
     adequately
    1.51
     slightest
    1.49
    anym
    1.44
     quelconque
    1.43
     żad
    1.42
     nici
    1.38
     alcuna
    1.36
     siquiera
    1.35
    Activations Density 2.568%

    No Known Activations