© 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. 2057
    Prev
    Next
    INDEX
    Explanations

    pauses and continuations

    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
    /
    0.98
    !
    0.73
    )
    0.71
    ِ
    0.70
    َ
    0.68
    ?
    0.68
    ло
    0.67
    !!!
    0.66
    во
    0.65
    就可以了
    0.65
    POSITIVE LOGITS
     spanning
    1.23
     embodying
    1.22
     dubbed
    1.22
     whose
    1.17
     replete
    1.17
     devoid
    1.16
     comprenant
    1.15
     જેને
    1.15
     ktorá
    1.14
    whose
    1.14
    Activations Density 1.249%

    No Known Activations