© 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. 1169
    Prev
    Next
    INDEX
    Explanations

    code comments and configurations

    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
     啊
    1.71
     갔
    1.61
     えっ
    1.60
     stupid
    1.60
     え
    1.59
     crazy
    1.56
     哦
    1.53
     뭐
    1.50
     했던
    1.50
     born
    1.49
    POSITIVE LOGITS
    これにより
    1.47
    Additional
    1.42
    additional
    1.42
    并在
    1.40
    Detailed
    1.40
    Alternatively
    1.39
    detailed
    1.33
    সমূ
    1.32
    इससे
    1.31
    Additionally
    1.30
    Activations Density 0.044%

    No Known Activations