© 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. 100304
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    一緒
    -1.45
    丰富的
    -1.30
    throm
    -1.29
     construcción
    -1.23
    dama
    -1.22
     and
    -1.22
    逦
    -1.22
     propia
    -1.20
    MediaStore
    -1.20
     tangled
    -1.19
    POSITIVE LOGITS
     his
    1.74
     أثناء
    1.51
    2
    1.48
    </strong>
    1.47
    这里
    1.43
    дцать
    1.38
     вслед
    1.35
    之一
    1.35
    ież
    1.31
    及其
    1.30
    Activations Density 0.002%

    No Known Activations