© 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. 9982
    Prev
    Next
    INDEX
    Explanations

    positional attributes (padding, margin, top, left)

    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
     cuando
    -1.57
    Ἦ
    -1.48
     dieser
    -1.48
    私たちは
    -1.45
    uarkan
    -1.42
    衎
    -1.42
    huile
    -1.41
    umbnail
    -1.41
    戩
    -1.41
    はこの
    -1.40
    POSITIVE LOGITS
     incred
    1.40
     It
    1.34
    を開始
    1.31
    a
    1.30
     solely
    1.30
     لأنه
    1.29
     only
    1.28
     sortir
    1.27
    ally
    1.27
     itinéraire
    1.26
    Activations Density 0.007%

    No Known Activations