© 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. 108140
    Prev
    Next
    INDEX
    Explanations

    legal or website disclaimers

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

    interrogative 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
    Helvetica
    0.49
    Ended
    0.48
    हिंदी
    0.48
    躋
    0.46
    Filename
    0.44
     በሽታ
    0.43
    遠
    0.43
    軟
    0.43
    ༣
    0.43
    अप्रैल
    0.43
    POSITIVE LOGITS
     Ehm
    0.54
     EO
    0.47
     cuando
    0.44
    onos
    0.44
     lorf
    0.44
     Eo
    0.44
     ambos
    0.44
     '*
    0.44
     custodians
    0.43
     मुर्
    0.43
    Activations Density 0.001%

    No Known Activations