© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19386
    Prev
    Next
    INDEX
    Explanations

    definition requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     увеличения
    0.76
    ፫
    0.71
     is
    0.70
     backgroundColor
    0.69
     点击
    0.69
     effectuer
    0.66
     =
    0.65
     with
    0.64
     WITH
    0.64
     предполага
    0.64
    POSITIVE LOGITS
    in
    1.12
    it
    1.00
    an
    0.99
    and
    0.91
    ん
    0.91
    as
    0.90
    定義
    0.89
    inę
    0.89
    o
    0.87
    un
    0.82
    Activations Density 0.084%

    No Known Activations