© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 12093
    Prev
    Next
    INDEX
    Explanations

    hair repair and strength

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

    structural analysis and materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tpVar
    0.45
    簸
    0.45
    ⵜ
    0.44
     земле
    0.44
    headphones
    0.44
     earphones
    0.43
     paysans
    0.42
    差别
    0.42
    敦
    0.42
    ྭ
    0.42
    POSITIVE LOGITS
     strand
    0.48
     brittle
    0.48
     flex
    0.47
     steel
    0.46
     repair
    0.46
     fracture
    0.46
     Fracture
    0.46
     Hair
    0.45
     Flex
    0.45
     Repair
    0.45
    Activations Density 0.042%

    No Known Activations