© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 226
    Prev
    Next
    INDEX
    Explanations

    avoids negative or excessive outputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
     unmistakable
    0.17
     konnten
    0.15
    three
    0.15
     pourront
    0.15
    都能
    0.15
     four
    0.14
    6
    0.14
    7
    0.14
     adjacent
    0.14
    neath
    0.14
    POSITIVE LOGITS
     needlessly
    0.27
     unnecessarily
    0.22
     unduly
    0.21
     risking
    0.21
     endangering
    0.21
    那么多
    0.21
     misuse
    0.21
     blindly
    0.21
     столь
    0.20
     jeopard
    0.20
    Activations Density 5.888%

    No Known Activations