© 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. 10835
    Prev
    Next
    INDEX
    Explanations

    this. `this.`

    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
     of
    -1.82
    ztes
    -1.56
    晦
    -1.44
     ?
    -1.43
     کنه
    -1.42
    濑
    -1.42
     vandaag
    -1.40
     vraag
    -1.39
    »?
    -1.38
     publier
    -1.38
    POSITIVE LOGITS
    how
    1.56
    𖤍
    1.52
    for
    1.52
    ynchronously
    1.50
     llevaba
    1.47
    new
    1.45
    屋外
    1.44
     }));
    1.44
    end
    1.41
    different
    1.38
    Activations Density 0.031%

    No Known Activations