© 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. 205786
    Prev
    Next
    INDEX
    Explanations

    place names and pronouns

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

    Microsoft has, fashioned oats, position while, for grooming, this passage, the specific, the ball, steel-cut oats, provided data, chase dreams

    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
     Sponsorship
    0.47
     Nullam
    0.46
     Thankfully
    0.45
     Controvers
    0.45
     Deadpool
    0.45
     Frankenstein
    0.44
     swoop
    0.44
    ῴ
    0.44
     ("[
    0.44
     codeword
    0.44
    POSITIVE LOGITS
    colors
    0.50
    с
    0.50
    ｄ
    0.49
    markets
    0.48
    progress
    0.48
     d
    0.48
    resistance
    0.47
    ふる
    0.47
    ufs
    0.46
    z
    0.46
    Activations Density 0.000%

    No Known Activations