© 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. 70024
    Prev
    Next
    INDEX
    Explanations

    "doing so," result

    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
    -1.73
     since
    -1.61
     until
    -1.45
    '>{
    -1.41
    このまま
    -1.40
     because
    -1.37
     lavoratori
    -1.35
    °;
    -1.33
    phosp
    -1.33
    polator
    -1.32
    POSITIVE LOGITS
     faisant
    1.55
     It
    1.51
     entièrement
    1.42
     promesse
    1.38
    使
    1.38
     sélectionné
    1.37
     Its
    1.36
    ჻
    1.34
     câmera
    1.34
     vôtre
    1.34
    Activations Density 0.008%

    No Known Activations