© 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. 67943
    Prev
    Next
    INDEX
    Explanations

    PHP documentation blocks

    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
     but
    -2.03
     to
    -1.52
    ("
    -1.45
     nace
    -1.43
    だったが
    -1.41
    ᅠ
    -1.41
    and
    -1.40
     the
    -1.39
    but
    -1.38
     emphasis
    -1.34
    POSITIVE LOGITS
     It
    1.89
     =
    1.82
    这里
    1.60
    已经是
    1.55
    讴
    1.47
     lances
    1.46
     düşünü
    1.42
    
    1.42
     gustado
    1.41
    情報は
    1.41
    Activations Density 0.004%

    No Known Activations