© 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. 68358
    Prev
    Next
    INDEX
    Explanations

    polycrystalline silicon

    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
     recoge
    -2.56
     Then
    -2.30
    檮
    -2.03
     regresa
    -1.97
     visitó
    -1.84
     famed
    -1.82
    -
    -1.80
     lends
    -1.79
     propone
    -1.76
     notoriously
    -1.73
    POSITIVE LOGITS
    我们
    1.84
    ا
    1.83
    ,”
    1.83
    e
    1.80
    satunya
    1.80
    6
    1.76
    1
    1.71
    Ｔ
    1.67
    ’
    1.65
    เพราะ
    1.63
    Activations Density 0.043%

    No Known Activations