© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162729
    Prev
    Next
    INDEX
    Explanations

    documentation and records

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

    this X is/are.

    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
    麃
    0.47
    行列
    0.45
    就在
    0.44
    碑
    0.44
    ديد
    0.44
    愧
    0.43
    و
    0.43
    ここ
    0.42
     bezpiecze
    0.41
    到一个
    0.41
    POSITIVE LOGITS
     SOLD
    0.46
     cooperated
    0.46
     Y
    0.44
     feathers
    0.44
     Lagos
    0.44
     Her
    0.44
     indigenous
    0.44
    CELL
    0.43
     OSU
    0.43
     BF
    0.43
    Activations Density 0.001%

    No Known Activations