© 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. 67198
    Prev
    Next
    INDEX
    Explanations

    titles and website names

    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
     münchen
    -1.68
    鲧
    -1.65
     stadt
    -1.62
     短发
    -1.61
    ⡃
    -1.59
     parachoque
    -1.58
    voces
    -1.57
     camiset
    -1.54
     our
    -1.54
     feroit
    -1.51
    POSITIVE LOGITS
    It
    1.86
     There
    1.76
     \
    1.68
    amaño
    1.65
    </b>
    1.64
     new
    1.61
    There
    1.59
    9
    1.55
     For
    1.53
    ко
    1.49
    Activations Density 0.124%

    No Known Activations