© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84594
    Prev
    Next
    INDEX
    Explanations

    get what you want

    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
     permitan
    -1.35
     dacă
    -1.31
    趼
    -1.29
    simply
    -1.27
     возможно
    -1.26
     you
    -1.24
     tenets
    -1.23
     your
    -1.23
     the
    -1.21
    iress
    -1.20
    POSITIVE LOGITS
    0
    1.53
    spě
    1.30
    くれる
    1.28
     started
    1.28
    5
    1.25
    7
    1.23
    哋
    1.20
    <
    1.17
    "
    1.16
     with
    1.15
    Activations Density 0.012%

    No Known Activations