© 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-16K
    7. 9694
    Prev
    Next
    INDEX
    Explanations

    or someone you know

    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_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
    horst
    1.18
    :\/\/
    1.07
    ſed
    1.07
    輸入品
    1.00
    \"\
    0.96
    (\
    0.93
    
    0.92
    エース
    0.92
    டுத்த
    0.92
    leon
    0.90
    POSITIVE LOGITS
    osit
    1.29
    安全性
    1.20
    attet
    1.19
    ahmat
    1.17
    鈣
    1.16
    แค
    1.15
    的安全
    1.15
     kap
    1.13
     تعیین
    1.13
    ivation
    1.12
    Activations Density 0.080%

    No Known Activations