© 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. 615
    Prev
    Next
    INDEX
    Explanations

    g followed by .,

    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
     face
    1.10
     ν
    1.09
     θ
    1.09
     tend
    1.04
     excess
    0.98
     conduction
    0.96
     intrinsically
    0.95
     premise
    0.94
     χ
    0.93
     molar
    0.93
    POSITIVE LOGITS
    などが
    1.63
    ,,,,
    1.52
    など
    1.51
     الخميس
    1.51
    などの
    1.47
    ช่วง
    1.42
    etc
    1.42
    、「
    1.42
    などを
    1.41
     โดย
    1.41
    Activations Density 0.046%

    No Known Activations