© 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. 13737
    Prev
    Next
    INDEX
    Explanations

    verbs of reporting speech

    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
     espagnol
    -1.13
    ”
    -1.11
    0
    -1.09
    ”.
    -1.07
     стали
    -1.00
    czyn
    -1.00
     évaluations
    -0.99
     apenas
    -0.99
    >
    -0.99
     only
    -0.98
    POSITIVE LOGITS
     also
    1.95
     inoltre
    1.45
     همچنین
    1.27
     tiež
    1.26
     също
    1.25
    ɶ
    1.25
     також
    1.24
    jąc
    1.24
    secuted
    1.23
     biasanya
    1.20
    Activations Density 0.038%

    No Known Activations