© 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-16K
    7. 2043
    Prev
    Next
    INDEX
    Explanations

    more than

    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
    2.37
    <bos>
    2.33
    ropoda
    2.19
     साली
    2.16
    sruhe
    2.12
    ("~/
    2.07
    aroos
    2.02
    ışt
    2.01
    很
    1.98
    很有
    1.97
    POSITIVE LOGITS
     than
    4.52
    Than
    3.77
    than
    3.68
     niż
    3.56
     Than
    3.30
     än
    3.15
     THAN
    2.91
     ніж
    2.71
    жели
    2.58
     kuin
    2.50
    Activations Density 0.820%

    No Known Activations