© 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. 180384
    Prev
    Next
    INDEX
    Explanations

    sequences or next steps

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

    we intuitively

    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
     jamás
    0.53
    ่
    0.51
     nikdy
    0.49
    ÔNG
    0.49
    thisTrack
    0.48
    setHeader
    0.47
     udě
    0.47
    FUNC
    0.46
     thisTrack
    0.46
    ='';
    0.46
    POSITIVE LOGITS
    下一步
    0.42
     their
    0.42
     because
    0.42
    iern
    0.41
     Peirce
    0.41
     the
    0.41
    氈
    0.40
     an
    0.40
     उनका
    0.40
     Zip
    0.40
    Activations Density 0.002%

    No Known Activations