© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47785
    Prev
    Next
    INDEX
    Explanations

    narrative descriptions and instructions

    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
    }
    -1.59
     tabPage
    -1.55
     masala
    -1.52
    まさかの
    -1.44
    ^{*
    -1.42
    (">
    -1.41
    ...:
    -1.40
    並沒有
    -1.39
     these
    -1.38
    お土産
    -1.38
    POSITIVE LOGITS
     –
    2.08
     if
    1.80
    </em>
    1.54
    </i>
    1.47
     since
    1.42
    if
    1.41
     as
    1.39
     unless
    1.38
    轳
    1.36
     ‘
    1.34
    Activations Density 0.006%

    No Known Activations