© 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. 99356
    Prev
    Next
    INDEX
    Explanations

    to followed by a verb

    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
    CascadeType
    -1.51
     there
    -1.51
    巨大的
    -1.48
    CardBody
    -1.48
    dafx
    -1.44
     е
    -1.42
     estos
    -1.42
    ECONDS
    -1.39
     minutes
    -1.38
     Windows
    -1.38
    POSITIVE LOGITS
     также
    1.66
     meerdere
    1.54
     نیز
    1.43
     possesso
    1.43
    覺得
    1.39
     նաև
    1.34
    oną
    1.32
     Igles
    1.32
     także
    1.31
    oczes
    1.30
    Activations Density 0.013%

    No Known Activations