© 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. 34-GEMMASCOPE-RES-131K
    7. 30483
    Prev
    Next
    INDEX
    Explanations

    give a quote or estimate

    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_34/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
    ข้าว
    -0.80
    érios
    -0.77
    PRIME
    -0.75
    ି
    -0.74
    خت
    -0.70
     Millionaire
    -0.70
    rum
    -0.70
     Miriam
    -0.69
    buyer
    -0.69
    ἅ
    -0.69
    POSITIVE LOGITS
     quote
    4.53
     quotes
    4.13
     quotation
    3.86
     quotations
    3.42
     quoted
    3.39
    quote
    3.36
     Quote
    3.34
     estimate
    3.30
    Quote
    3.16
     Quotes
    3.14
    Activations Density 0.050%

    No Known Activations