© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9390
    Prev
    Next
    INDEX
    Explanations

    tells you

    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
    뒀
    1.23
     тему
    1.20
    striées
    1.20
     buồn
    1.19
    贛
    1.19
     thùng
    1.18
    citenamefont
    1.17
     повер
    1.16
    װ
    1.14
    textepsilon
    1.14
    POSITIVE LOGITS
     Accordingly
    1.01
     Therefore
    0.99
     Suitable
    0.98
    Suitable
    0.98
     feasible
    0.98
     Possible
    0.96
     Compatibility
    0.96
    <sub>
    0.95
     feasibility
    0.95
     Driving
    0.94
    Activations Density 0.014%

    No Known Activations