© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10058
    Prev
    Next
    INDEX
    Explanations

    can search for

    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_22_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
    응
    0.84
    鸦
    0.81
    uro
    0.76
     मुर्
    0.75
     Indic
    0.75
    kunde
    0.70
    요
    0.70
     நூல்
    0.69
     tonight
    0.69
    산
    0.69
    POSITIVE LOGITS
     arthrop
    1.08
     lensing
    0.99
    Step
    0.97
    Robust
    0.94
    乐趣
    0.93
    Wear
    0.93
    Hack
    0.93
    stepping
    0.92
     মজা
    0.92
    Jacobi
    0.91
    Activations Density 0.065%

    No Known Activations