© 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. 14184
    Prev
    Next
    INDEX
    Explanations

    pulling up or into

    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
     mesmas
    -2.17
     primeiras
    -1.86
    ाउनलोड
    -1.74
    ℣
    -1.63
    曁
    -1.59
     nuevo
    -1.57
    ocidade
    -1.57
     antigas
    -1.52
     skal
    -1.52
     they
    -1.52
    POSITIVE LOGITS
    REEK
    1.76
    ༷
    1.67
    有何
    1.66
     :).
    1.63
    数が
    1.59
     respective
    1.56
     einwand
    1.55
    })=\
    1.51
    问题的
    1.46
     Produkten
    1.45
    Activations Density 0.005%

    No Known Activations