© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13181
    Prev
    Next
    INDEX
    Explanations

    purpose or function

    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
    內容簡介
    -1.44
     maceta
    -1.29
    厲害
    -1.27
    єра
    -1.27
    进入了
    -1.25
     reconocido
    -1.25
    ついに
    -1.24
    过来了
    -1.21
    poir
    -1.21
    zelfde
    -1.21
    POSITIVE LOGITS
    si
    1.67
    be
    1.67
    ka
    1.61
    u
    1.56
    h
    1.54
    ca
    1.53
     "
    1.51
    lo
    1.46
    pp
    1.45
     “
    1.45
    Activations Density 0.066%

    No Known Activations