© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47016
    Prev
    Next
    INDEX
    Explanations

    tortoise and turtle

    np_acts-logits-general · gemini-2.5-flash-lite

    words referring to turtles or tortoises.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    Negative Logits
     précédent
    -0.77
    тья
    -0.74
     официаль
    -0.73
    ԋ
    -0.72
     Electrochemical
    -0.71
    修士
    -0.71
     تھا
    -0.71
    architecture
    -0.71
     enfant
    -0.70
    orient
    -0.70
    POSITIVE LOGITS
     tortoise
    1.41
     turtle
    1.35
    dove
    1.19
     Tortoise
    1.17
     torto
    1.10
     Turtle
    1.09
    Turtle
    1.07
    turtle
    1.05
     turtles
    0.98
     snail
    0.90
    Activations Density 0.023%

    No Known Activations