© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2266
    Prev
    Next
    INDEX
    Explanations

    numeric input errors

    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_65k_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
    。
    1.15
    。)
    1.00
    )。
    0.99
    ।
    0.97
    」。
    0.93
    ]。
    0.88
    ؛
    0.85
     。
    0.85
    ፡
    0.83
    粵
    0.80
    POSITIVE LOGITS
     אפ
    0.89
    ß
    0.73
    িও
    0.71
    ົນ
    0.71
     bimestre
    0.71
    சை
    0.69
     פאר
    0.68
    שת
    0.68
     erscheinen
    0.67
    ວດ
    0.67
    Activations Density 0.017%

    No Known Activations