© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111750
    Prev
    Next
    INDEX
    Explanations

    abbreviations and their meanings

    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
    เพราะ
    -1.33
    ньому
    -1.33
    ämpfer
    -1.21
     två
    -1.19
     hogyan
    -1.16
    yorsunuz
    -1.16
     châssis
    -1.15
     защото
    -1.13
     вони
    -1.13
    hibits
    -1.13
    POSITIVE LOGITS
    le
    1.23
     to
    1.22
    </b>
    1.17
    alers
    1.16
     again
    1.13
    __()
    1.13
     necessary
    1.12
     отно
    1.11
     something
    1.10
     nesse
    1.10
    Activations Density 0.255%

    No Known Activations