© 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. 185008
    Prev
    Next
    INDEX
    Explanations

    download, fuels, sequence

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

    comprehensive, strategic, thorough

    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
     atra
    0.61
     usando
    0.55
     atract
    0.52
     usamos
    0.51
    .@
    0.50
     strangled
    0.48
    ंका
    0.47
     creando
    0.47
    たん
    0.46
     ܥ
    0.46
    POSITIVE LOGITS
    म्मी
    0.46
     Sequence
    0.45
     FUEL
    0.44
     Fuels
    0.43
    মাণের
    0.43
    ެއް
    0.43
    صیلی
    0.42
     refundable
    0.41
     Psycho
    0.40
     Fuel
    0.40
    Activations Density 0.001%

    No Known Activations