© 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. 113261
    Prev
    Next
    INDEX
    Explanations

    words starting with Mos

    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
    ⚣
    -2.59
    龊
    -2.48
     schlechte
    -2.44
    两年
    -2.42
     preciosa
    -2.34
    麁
    -2.31
    を使
    -2.31
    一点点
    -2.30
    ᯾
    -2.30
    想了想
    -2.27
    POSITIVE LOGITS
     Your
    3.17
    鬭
    3.16
    \
    2.70
    栳
    2.69
    }$
    2.67
    *}\
    2.66
    {
    2.59
    *}$
    2.58
     are
    2.52
    *
    2.47
    Activations Density 0.006%

    No Known Activations