© 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. 86305
    Prev
    Next
    INDEX
    Explanations

    specific material or entity

    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
     and
    -2.30
     their
    -2.09
     who
    -1.87
     by
    -1.76
     using
    -1.58
    omenclature
    -1.50
     whose
    -1.46
     what
    -1.40
     ihre
    -1.39
     first
    -1.36
    POSITIVE LOGITS
     mantend
    1.59
     forbindelse
    1.58
     estrema
    1.58
     particolari
    1.57
     anledning
    1.51
     ayudará
    1.49
     harán
    1.46
     сегодня
    1.42
     particolare
    1.41
     udah
    1.39
    Activations Density 0.475%

    No Known Activations