© 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. 86181
    Prev
    Next
    INDEX
    Explanations

    verbs and continuations

    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
    ↵↵↵
    -1.38
    assertAll
    -1.38
    idlertid
    -1.38
     başlay
    -1.37
    mathrm
    -1.35
    OBJET
    -1.27
    除了
    -1.27
    ؋
    -1.25
     ediyor
    -1.25
     like
    -1.24
    POSITIVE LOGITS
     anunciou
    1.63
     anún
    1.59
    鹀
    1.55
     but
    1.52
     secrétaire
    1.51
     fantastique
    1.41
    ЙТЕ
    1.41
     revelou
    1.37
    ейчас
    1.35
     voltou
    1.35
    Activations Density 0.360%

    No Known Activations