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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10836
    Prev
    Next
    INDEX
    Explanations

    things that happen sometimes

    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
    ​
    0.90
     Russo
    0.84
    <i>
    0.80
    비
    0.79
    ‏
    0.78
     called
    0.76
     Driscoll
    0.76
     Перейти
    0.75
    ̄
    0.74
    ーーーー
    0.72
    POSITIVE LOGITS
     potable
    1.18
     üret
    1.17
     líqu
    1.16
    orgt
    1.15
    áce
    1.13
    permit
    1.13
    áč
    1.12
     leachate
    1.11
     permit
    1.11
    鳕
    1.10
    Activations Density 1.405%

    No Known Activations