© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9224
    Prev
    Next
    INDEX
    Explanations

    areas for improvement

    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
     ſ
    1.11
     fester
    0.97
    ാര്‍
    0.88
     innumerable
    0.85
     vielf
    0.82
     conquering
    0.81
     bich
    0.80
     slaying
    0.80
     Teut
    0.78
    牠
    0.78
    POSITIVE LOGITS
     }}(\
    1.60
     (%
    1.58
     }()
    1.57
    erView
    1.55
     (?
    1.50
    McC
    1.50
     (“
    1.49
     }(\
    1.47
    MktCap
    1.47
    /(
    1.46
    Activations Density 0.059%

    No Known Activations