© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70592
    Prev
    Next
    INDEX
    Explanations

    contrasting things

    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
    </strong>
    -1.32
    s
    -1.27
     Organisator
    -1.27
     recent
    -1.24
    喈
    -1.23
     sufrimiento
    -1.21
    Ꮸ
    -1.20
    はっきり
    -1.20
     hará
    -1.19
     avait
    -1.17
    POSITIVE LOGITS
     than
    1.95
     different
    1.82
     distinta
    1.58
     they
    1.55
     distinto
    1.48
    GraphicsUnit
    1.42
     niż
    1.40
     مختلف
    1.38
    getSystemService
    1.37
    Than
    1.34
    Activations Density 0.064%

    No Known Activations