© 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. 13860
    Prev
    Next
    INDEX
    Explanations

    providing answers or yes/no responses

    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
     of
    -1.35
    nados
    -1.34
    ↵↵
    -1.34
     and
    -1.32
    🛠
    -1.21
    ynth
    -1.18
    ？”
    -1.17
    ńcu
    -1.16
    。”
    -1.14
     juft
    -1.13
    POSITIVE LOGITS
     about
    1.62
     schwach
    1.46
    わかった
    1.40
    HasValue
    1.37
     dangers
    1.31
    fillType
    1.27
     terapé
    1.27
     Unterstüt
    1.26
     uncover
    1.25
     cotidiano
    1.25
    Activations Density 0.050%

    No Known Activations