© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13499
    Prev
    Next
    INDEX
    Explanations

    assuming or assumed

    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
     '
    -2.38
     '-
    -2.22
     '#
    -2.08
    でも
    -2.02
    崀
    -1.98
    !"
    -1.97
    ='
    -1.97
     $>
    -1.95
     $<
    -1.91
    鍆
    -1.88
    POSITIVE LOGITS
     that
    2.14
    ↵
    1.95
    ,
    1.80
     because
    1.79
    :
    1.64
     widespread
    1.63
     большого
    1.56
    assume
    1.53
    Want
    1.52
     壓
    1.51
    Activations Density 0.025%

    No Known Activations