© 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. 127207
    Prev
    Next
    INDEX
    Explanations

    common prepositional phrases

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

    non-english characters

    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
    ม
    0.53
    project
    0.46
    羿
    0.46
    personality
    0.46
    font
    0.45
    phabet
    0.45
    php
    0.45
    Civ
    0.44
    ز
    0.44
    scholar
    0.44
    POSITIVE LOGITS
     அடிக்கடி
    0.62
     sağlı
    0.60
     pronunci
    0.59
     incó
    0.55
     măsur
    0.55
     технологі
    0.55
     অতিরিক্ত
    0.55
     concomit
    0.55
    getCQL
    0.54
     dredging
    0.53
    Activations Density 0.000%

    No Known Activations