© 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. 144102
    Prev
    Next
    INDEX
    Explanations

    talking about or position in

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

    generating text with specific constraints

    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
    し
    0.54
    绉
    0.53
    ることができる
    0.52
    اری
    0.50
    总统
    0.50
     Được
    0.50
    До
    0.49
    ศ
    0.49
    鼕
    0.49
     Provided
    0.48
    POSITIVE LOGITS
    ing
    0.57
    bud
    0.52
    mena
    0.51
    flight
    0.51
    rip
    0.50
    opting
    0.50
    ven
    0.50
    quantum
    0.48
    hearted
    0.48
    ed
    0.46
    Activations Density 0.000%

    No Known Activations