© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 860
    Prev
    Next
    INDEX
    Explanations

    code or special characters

    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
     and
    -2.08
    嵎
    -1.99
    </
    -1.59
    และ
    -1.58
    the
    -1.42
    與
    -1.41
    ando
    -1.40
     quatre
    -1.39
    xffff
    -1.39
    翼翼
    -1.38
    POSITIVE LOGITS
     when
    1.66
     that
    1.57
     not
    1.56
    álna
    1.52
     all
    1.52
    自然的
    1.51
     which
    1.49
     Then
    1.43
    Quotation
    1.42
    Epoxy
    1.39
    Activations Density 0.000%

    No Known Activations