© 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. 68161
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun/determiner

    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
     which
    -1.75
     and
    -1.59
     or
    -1.53
     tells
    -1.45
    plained
    -1.44
     that
    -1.41
     extensively
    -1.41
     intricate
    -1.40
     enables
    -1.38
     After
    -1.36
    POSITIVE LOGITS
     малень
    1.79
    9
    1.67
     mâle
    1.66
    4
    1.62
    useNewUrlParser
    1.59
    }
    1.59
    7
    1.58
     ſmall
    1.55
    поги
    1.54
    ’
    1.52
    Activations Density 0.049%

    No Known Activations