© 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. 10565
    Prev
    Next
    INDEX
    Explanations

    daughter of

    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
     altri
    -1.45
    쐈
    -1.44
     viewDidLoad
    -1.41
     ISSUED
    -1.36
    konos
    -1.35
     []:
    -1.35
     otros
    -1.34
     mahdol
    -1.31
     ($('#
    -1.31
     garant
    -1.31
    POSITIVE LOGITS
     by
    1.84
     the
    1.45
     what
    1.42
    illite
    1.35
     that
    1.34
     who
    1.34
     their
    1.34
     both
    1.31
     an
    1.30
     one
    1.27
    Activations Density 0.141%

    No Known Activations