© 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. 130149
    Prev
    Next
    INDEX
    Explanations

    actions followed by nouns

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

    handling historical readings, volunteered, products, feelings

    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
    an
    0.49
    i
    0.49
    was
    0.47
    edel
    0.47
    nung
    0.46
    on
    0.46
    disco
    0.45
    chess
    0.45
     உண்
    0.45
    cre
    0.44
    POSITIVE LOGITS
     vowels
    0.49
     eliminar
    0.48
    跻
    0.48
     opcion
    0.48
     elimin
    0.46
     separators
    0.46
     obj
    0.46
     armature
    0.46
     adhesions
    0.45
     ordinal
    0.45
    Activations Density 0.000%

    No Known Activations