© 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. 91219
    Prev
    Next
    INDEX
    Explanations

    governance and funds

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

    offer options or terms

    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
     Zusch
    0.50
     yönt
    0.49
     operatives
    0.48
     photons
    0.45
     Organisation
    0.44
    ()}")
    0.43
    ਿਆਂ
    0.43
    疏
    0.43
    টেলে
    0.43
     méthode
    0.42
    POSITIVE LOGITS
    ann
    0.50
    iences
    0.47
    akaranam
    0.46
    onant
    0.44
    elp
    0.44
    auru
    0.44
    elic
    0.43
    安定
    0.43
    entering
    0.42
    onance
    0.42
    Activations Density 0.000%

    No Known Activations