© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107564
    Prev
    Next
    INDEX
    Explanations

    assessment and evidence

    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
    Siblings
    -0.78
    Clever
    -0.75
     รัก
    -0.74
    colourful
    -0.73
    Silen
    -0.73
     Бор
    -0.73
     Prin
    -0.73
    二重
    -0.73
     earphones
    -0.72
    balenciaga
    -0.72
    POSITIVE LOGITS
     evidence
    1.49
    Evidence
    1.21
    evidence
    1.16
     Assessor
    1.16
     assessor
    1.13
     Evidence
    1.06
     assessors
    1.05
     workplace
    1.03
     task
    0.94
     underpin
    0.91
    Activations Density 0.009%

    No Known Activations