© 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. 40534
    Prev
    Next
    INDEX
    Explanations

    mathematical comparisons and sequences

    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
     construit
    -1.53
     bricola
    -1.51
     skle
    -1.45
     pewno
    -1.44
     alarme
    -1.42
    磻
    -1.40
    🪆
    -1.37
    髫
    -1.37
     then
    -1.35
    虓
    -1.35
    POSITIVE LOGITS
     you
    1.66
     ので
    1.49
    pecabe
    1.48
    textEdit
    1.47
    죽
    1.45
     gång
    1.41
     않았
    1.40
    옅
    1.40
     eivät
    1.38
    ԝ
    1.38
    Activations Density 0.009%

    No Known Activations