© 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. 141264
    Prev
    Next
    INDEX
    Explanations

    divisional performance, minimum

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

    file, libraries, games, options, instructions

    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
    Negative Logits
    ки
    0.45
     
    0.44
    Machine
    0.42
    ï
    0.41
    merce
    0.41
    Saf
    0.41
     機
    0.41
    Retry
    0.40
     便
    0.40
     .
    0.40
    POSITIVE LOGITS
     hoger
    0.54
     रिवाइज
    0.53
    Aeonium
    0.53
    ፍተኛ
    0.51
    ającym
    0.50
     vincul
    0.50
     tertinggi
    0.48
    чними
    0.48
     obowiąz
    0.48
     behe
    0.48
    Activations Density 0.001%

    No Known Activations