© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12442
    Prev
    Next
    INDEX
    Explanations

    prepositions and interrogatives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ✪
    1.33
     daging
    1.31
     ఒక్క
    1.26
     publicaciones
    1.22
     aceptación
    1.22
     denitrification
    1.20
    ꔹ
    1.18
     perished
    1.16
     obrig
    1.14
    KSpriteNode
    1.14
    POSITIVE LOGITS
    er
    1.61
    ER
    1.57
    り
    1.57
    us
    1.36
    ли
    1.35
    lin
    1.35
    с
    1.34
    be
    1.31
    र
    1.31
    IC
    1.23
    Activations Density 0.000%

    No Known Activations