© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26264
    Prev
    Next
    INDEX
    Explanations

    words starting with Bla or Bl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ズニー
    -2.67
     (‘
    -2.63
    ſti
    -2.59
    玧
    -2.56
    ㌧
    -2.55
    TintMode
    -2.52
    ญี่ป
    -2.52
    瞜
    -2.50
    acterium
    -2.48
    
    -2.48
    POSITIVE LOGITS
    2
    4.34
    3
    3.72
    1
    3.72
    8
    3.30
    9
    2.95
    “
    2.94
    6
    2.92
    4
    2.92
    [
    2.89
    *
    2.84
    Activations Density 0.030%

    No Known Activations