© 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. 63192
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
     Doesn
    -1.13
    ᅯ
    -1.10
     Featuring
    -1.09
    uſe
    -1.06
     Describes
    -1.05
    跻
    -1.05
     startling
    -1.02
    eake
    -1.02
     Pulling
    -1.00
     reasons
    -1.00
    POSITIVE LOGITS
     answered
    1.95
     unanswered
    1.82
     posed
    1.77
     asked
    1.73
     about
    1.55
    questions
    1.55
    answered
    1.52
    answers
    1.46
     QUESTIONS
    1.38
    Answers
    1.37
    Activations Density 0.045%

    No Known Activations