© 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. 21991
    Prev
    Next
    INDEX
    Explanations

    descriptive states or attributes

    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
     if
    -1.48
    riceps
    -1.35
    phere
    -1.27
     モ
    -1.27
    );//
    -1.25
    ();//
    -1.20
    oplus
    -1.20
    rit
    -1.20
     «
    -1.19
     a
    -1.18
    POSITIVE LOGITS
     rövid
    1.57
    narod
    1.38
    Контак
    1.36
     frenos
    1.34
     gyóg
    1.34
     gyors
    1.33
     such
    1.31
    saco
    1.30
     września
    1.29
     hosszú
    1.29
    Activations Density 0.353%

    No Known Activations