© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130394
    Prev
    Next
    INDEX
    Explanations

    program keywords and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     burgeoning
    -2.30
     After
    -2.28
     unparalleled
    -2.27
     sizable
    -2.25
    .
    -2.23
    there
    -2.19
     abundant
    -2.17
     two
    -2.16
     four
    -2.14
     markedly
    -2.13
    POSITIVE LOGITS
     specif
    2.28
    刄
    2.20
     solamente
    2.13
    齶
    2.09
    快要
    2.09
     -.
    2.08
     castig
    2.08
     cuatro
    2.08
     …..
    2.02
    莇
    2.02
    Activations Density 0.026%

    No Known Activations