© 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. 103257
    Prev
    Next
    INDEX
    Explanations

    "or so", "or two", "or less"

    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
     from
    -1.79
    淠
    -1.79
     provides
    -1.66
     bereits
    -1.66
     料金
    -1.63
    嫆
    -1.63
     berbahaya
    -1.56
     Each
    -1.55
     aneh
    -1.54
     Like
    -1.53
    POSITIVE LOGITS
     
    2.34
     "",
    1.84
     „
    1.70
     "";
    1.70
    »,
    1.66
     ago
    1.65
     me
    1.55
    ’
    1.55
     \
    1.54
     –
    1.54
    Activations Density 0.009%

    No Known Activations