© 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. 154766
    Prev
    Next
    INDEX
    Explanations

    father needs

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

    Greek alphabet

    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
     ."
    0.56
     .”
    0.53
     .)
    0.46
    ંકી
    0.44
    :["
    0.44
     ойноо
    0.44
    峹
    0.44
    喲
    0.44
    呦
    0.42
    COLOG
    0.42
    POSITIVE LOGITS
    试图
    0.49
    ing
    0.48
    总是
    0.47
     versuchen
    0.47
     حس
    0.46
     heg
    0.46
    Ptr
    0.45
     أساس
    0.44
     numérica
    0.44
     appre
    0.42
    Activations Density 0.001%

    No Known Activations