© 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
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2555
    Prev
    Next
    INDEX
    Explanations

    introduces contrast or addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    *,
    1.08
    ;,
    1.06
    +,
    1.04
     તેમજ
    0.98
     ஆகியவை
    0.98
     ;,
    0.97
     –,
    0.97
    ?,
    0.96
    ,[
    0.95
     -,
    0.94
    POSITIVE LOGITS
     these
    0.87
     contradictory
    0.78
    soever
    0.78
     untrue
    0.77
     noteworthy
    0.74
     paradoxical
    0.74
    そのような
    0.72
     troubling
    0.71
    lest
    0.70
    forth
    0.69
    Activations Density 0.217%

    No Known Activations