© 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. 34-GEMMASCOPE-RES-131K
    7. 47906
    Prev
    Next
    INDEX
    Explanations

    any software

    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_34/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
     内衣
    -1.25
     certains
    -1.21
     ſome
    -1.21
     exacte
    -1.13
     opini
    -1.13
    gingen
    -1.13
     intrig
    -1.11
     manifeste
    -1.10
     stesso
    -1.09
     tomate
    -1.07
    POSITIVE LOGITS
     or
    2.72
     whatsoever
    2.45
     imaginable
    2.38
     that
    2.23
     including
    2.19
     you
    2.08
     except
    1.77
     regardless
    1.70
    including
    1.59
     any
    1.57
    Activations Density 0.065%

    No Known Activations