© 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. 247124
    Prev
    Next
    INDEX
    Explanations

    education for children

    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
     ductility
    0.51
     dependences
    0.51
     =-\
    0.50
    ónico
    0.49
     قومی
    0.49
     Forming
    0.48
     isotropy
    0.48
     interdependence
    0.48
     அனுப
    0.47
     લગભગ
    0.47
    POSITIVE LOGITS
    Evet
    0.55
    K
    0.48
     rebord
    0.46
    Kan
    0.46
    erk
    0.45
    Textbox
    0.44
    卡
    0.44
     Jos
    0.43
    fo
    0.43
    Preset
    0.43
    Activations Density 0.001%

    No Known Activations