© 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. 110013
    Prev
    Next
    INDEX
    Explanations

    future trends urban online

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

    addition subtraction multiplication

    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
    า
    0.52
    下に
    0.45
    ρα
    0.45
    下の
    0.45
    賴
    0.44
    姿勢
    0.42
    承诺
    0.42
    dice
    0.41
    곶
    0.41
    CONFIGURE
    0.41
    POSITIVE LOGITS
     interrogated
    0.57
     woh
    0.52
     imitated
    0.52
     ún
    0.50
    член
    0.49
    wegian
    0.47
     accidentally
    0.47
     Ambro
    0.47
    arta
    0.46
     ambigu
    0.46
    Activations Density 0.001%

    No Known Activations