© 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. 119779
    Prev
    Next
    INDEX
    Explanations

    continual support and classes

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

    cause or contributing factors

    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
    िंग
    0.48
     دخول
    0.47
    堹
    0.46
     Situated
    0.45
     partecipanti
    0.45
    aldo
    0.45
    $-$
    0.44
    emoration
    0.44
    胙
    0.43
     Located
    0.43
    POSITIVE LOGITS
    य
    0.51
     auricul
    0.49
     be
    0.48
     simonsen
    0.48
     scrutin
    0.47
     patient
    0.46
     excurs
    0.46
     le
    0.46
     o
    0.46
     short
    0.46
    Activations Density 0.000%

    No Known Activations