© 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. 71480
    Prev
    Next
    INDEX
    Explanations

    special day occasion

    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
    理会
    -1.51
    atoday
    -1.44
     recibiendo
    -1.44
     anstatt
    -1.41
    hiker
    -1.41
    rave
    -1.36
    poche
    -1.32
    ஜ
    -1.30
    },
    -1.30
     luchar
    -1.29
    POSITIVE LOGITS
    Mucha
    1.46
    翃
    1.44
    sandalia
    1.44
    вні
    1.43
     reaksi
    1.39
     enthou
    1.36
    ❢
    1.33
     vaid
    1.32
    ACKNOWLEDG
    1.30
     vocale
    1.30
    Activations Density 0.032%

    No Known Activations