© 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. 73420
    Prev
    Next
    INDEX
    Explanations

    for + noun phrase

    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
     need
    -1.63
     după
    -1.59
     especially
    -1.44
     především
    -1.42
     more
    -1.38
     seems
    -1.38
     atât
    -1.35
     be
    -1.34
     not
    -1.33
    情況
    -1.31
    POSITIVE LOGITS
     to
    1.98
    ᐕ
    1.77
    蓠
    1.63
     rezultat
    1.61
    .’
    1.60
     zove
    1.59
    andidat
    1.57
     جميع
    1.52
     otros
    1.47
     taas
    1.41
    Activations Density 0.031%

    No Known Activations