© 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. 31-GEMMASCOPE-2-RES-262K
    7. 22932
    Prev
    Next
    INDEX
    Explanations

    mechanical parts and movement

    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_31_width_262k_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
     конференции
    0.46
    SEVERE
    0.45
    𝘸
    0.44
     प्रोसेसिंग
    0.43
    vrdr
    0.43
    戦略
    0.43
    語
    0.42
    𝙃
    0.42
    ご利用
    0.42
    itochond
    0.42
    POSITIVE LOGITS
     mechanism
    0.91
     movable
    0.84
     levers
    0.83
     sliding
    0.81
     lever
    0.80
     moveable
    0.80
     mécanisme
    0.80
     Mechanism
    0.79
     mekanisme
    0.77
     slider
    0.75
    Activations Density 0.075%

    No Known Activations