© 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. 59162
    Prev
    Next
    INDEX
    Explanations

    of followed by noun

    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
    5
    -3.22
    8
    -3.20
    0
    -3.09
    9
    -3.06
    6
    -2.94
    4
    -2.78
    7
    -2.55
     are
    -2.42
     adventures
    -2.34
    The
    -2.30
    POSITIVE LOGITS
    ︲
    2.86
    ⚣
    2.75
     They
    2.69
     illustrate
    2.67
    我先
    2.48
    潆
    2.48
    晅
    2.34
    yelitis
    2.33
    を作って
    2.30
    毐
    2.28
    Activations Density 16.326%

    No Known Activations