© 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. 85088
    Prev
    Next
    INDEX
    Explanations

    ease and no worries

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

    problem/solution and scoring

    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
    zeigt
    0.53
    ých
    0.51
     மிகப்
    0.50
    wechsel
    0.49
     Bedingungen
    0.49
     betrokken
    0.49
    劣化
    0.49
    峀
    0.48
    瞰
    0.48
    ntz
    0.47
    POSITIVE LOGITS
     errand
    0.55
     the
    0.54
     formality
    0.53
     du
    0.50
    in
    0.50
     director
    0.50
     (?,
    0.50
     literacy
    0.49
     uri
    0.49
     institute
    0.49
    Activations Density 0.002%

    No Known Activations