© 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. 22-GEMMASCOPE-RES-131K
    7. 65466
    Prev
    Next
    INDEX
    Explanations

    web development platforms

    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_22/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
     besucht
    -1.24
     jepang
    -1.23
     piccoli
    -1.23
     these
    -1.22
     sabbia
    -1.21
    These
    -1.20
    Instead
    -1.19
    When
    -1.19
    Every
    -1.18
    Again
    -1.18
    POSITIVE LOGITS
     inspección
    1.17
    ämie
    1.16
    ﻷ
    1.15
     گوشی
    1.12
     user
    1.07
    ྒ
    1.06
     platform
    1.06
     software
    1.05
     beğ
    1.05
     aplicação
    1.05
    Activations Density 0.200%

    No Known Activations