© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153299
    Prev
    Next
    INDEX
    Explanations

    noun/adjective + possessive pronoun or preposition

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

    basics and zero

    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
    Negative Logits
     continuity
    0.47
     uniformity
    0.45
     まま
    0.44
     mentorship
    0.44
     literacy
    0.44
    ዚ
    0.43
     romance
    0.42
     hijab
    0.42
     preference
    0.41
     minority
    0.41
    POSITIVE LOGITS
     που
    0.42
    ϖ
    0.41
    üse
    0.41
    子が
    0.40
    んで
    0.39
    ที่คุณ
    0.38
    assertTrue
    0.38
    restart
    0.38
     நிறைந்த
    0.37
    ема
    0.37
    Activations Density 0.008%

    No Known Activations