© 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. 10-GEMMASCOPE-RES-131K
    7. 58740
    Prev
    Next
    INDEX
    Explanations

    cabin or Kab names

    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_10/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
     of
    -2.70
    ⟣
    -2.55
    makeat
    -2.50
     které
    -2.50
    洳
    -2.42
     seleccionadas
    -2.38
    좆
    -2.33
     unſ
    -2.22
    毉
    -2.19
    
    -2.19
    POSITIVE LOGITS
    section
    3.16
    u
    2.80
    item
    2.70
    r
    2.59
    t
    2.55
    d
    2.44
    s
    2.39
    g
    2.38
    m
    2.36
    Much
    2.33
    Activations Density 0.003%

    No Known Activations