© 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. 73245
    Prev
    Next
    INDEX
    Explanations

    we are followed by descriptors

    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
     to
    -2.14
     üblichen
    -1.95
     beliebtesten
    -1.59
     einzigartigen
    -1.56
    euvres
    -1.53
     instead
    -1.46
     descrizione
    -1.45
     eigentlichen
    -1.44
     bezogen
    -1.44
    jenigen
    -1.40
    POSITIVE LOGITS
     juges
    1.45
     fria
    1.39
    抠
    1.37
    ꪔ
    1.33
     такую
    1.32
     õ
    1.30
     perfe
    1.29
    柃
    1.28
    是从
    1.28
     a
    1.28
    Activations Density 0.107%

    No Known Activations