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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6683
    Prev
    Next
    INDEX
    Explanations

    my perfectRatings world of

    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
    ing
    1.26
    ുകള്‍
    1.18
    t
    1.15
    ai
    1.14
     but
    1.11
    ,
    1.11
    ia
    1.10
     standardised
    1.10
    /
    1.08
    ide
    1.08
    POSITIVE LOGITS
    jdField
    1.57
     veľmi
    1.53
    exitTool
    1.52
    ম্ত
    1.46
    takePhotoButton
    1.44
    𒂗
    1.42
     nagyon
    1.42
     veliki
    1.41
     poz
    1.41
     اسے
    1.40
    Activations Density 0.000%

    No Known Activations