© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249530
    Prev
    Next
    INDEX
    Explanations

    directional or symmetrical relationships

    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
    שות
    0.48
    聽到
    0.45
     că
    0.41
     calmodulin
    0.41
     Improvements
    0.40
    虧
    0.40
     cyt
    0.40
     dataGenerator
    0.39
    抬
    0.39
    }\}
    0.38
    POSITIVE LOGITS
     दिशा
    0.50
     направление
    0.47
     symmetrical
    0.46
     Timo
    0.46
     Forza
    0.46
     Süden
    0.45
    idirectional
    0.45
     மற்றொரு
    0.45
     Seafood
    0.43
    utile
    0.43
    Activations Density 0.000%

    No Known Activations