© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9147
    Prev
    Next
    INDEX
    Explanations

    rope and cable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createArticle
    0.47
    勳
    0.46
    殼
    0.44
    詆
    0.42
    剜
    0.41
     persecuted
    0.41
    tablet
    0.41
    gameOver
    0.41
    emene
    0.41
    qués
    0.40
    POSITIVE LOGITS
     rope
    1.70
     ropes
    1.59
     Rope
    1.48
    绳
    1.47
     knot
    1.34
     knots
    1.34
    繩
    1.33
     dây
    1.32
     cables
    1.28
     cable
    1.27
    Activations Density 0.256%

    No Known Activations