© 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. 86945
    Prev
    Next
    INDEX
    Explanations

    systems and activities

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

    class of

    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
     память
    0.49
    граммы
    0.47
     когда
    0.47
     información
    0.44
     اث
    0.44
     restore
    0.43
     लिखने
    0.43
    결
    0.43
     लेखन
    0.43
     लिखना
    0.43
    POSITIVE LOGITS
    issaient
    0.48
    issait
    0.47
    ardini
    0.44
    qe
    0.44
     stairs
    0.43
    ula
    0.43
     investors
    0.42
    ai
    0.41
    iseum
    0.41
     lawmakers
    0.40
    Activations Density 0.005%

    No Known Activations