© 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. 172021
    Prev
    Next
    INDEX
    Explanations

    father figures and death doulas

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

    counting words or phrases

    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
    м
    0.55
    ing
    0.50
    v
    0.48
    lichting
    0.46
     kone
    0.45
    pesar
    0.45
     pesar
    0.44
    nicht
    0.44
    un
    0.44
    ating
    0.43
    POSITIVE LOGITS
     Skilled
    0.53
    教堂
    0.53
     houseplants
    0.52
     Waterproof
    0.51
     Aquarium
    0.50
     Audiobook
    0.50
    Ꮀ
    0.50
     Wildlife
    0.49
     Plumbing
    0.48
    睞
    0.48
    Activations Density 0.001%

    No Known Activations