© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68520
    Prev
    Next
    INDEX
    Explanations

    Code file paths and documentation

    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
     дър
    -1.21
     tournoi
    -1.19
     jurídico
    -1.16
     различни
    -1.14
     вашем
    -1.12
    laura
    -1.11
    england
    -1.09
     LAW
    -1.08
     BOOKS
    -1.07
     каждом
    -1.06
    POSITIVE LOGITS
    途
    1.13
    </u>
    1.07
    から
    1.02
    private
    1.01
    </i>
    1.01
    else
    0.99
     основ
    0.98
    is
    0.96
    적인
    0.95
     posh
    0.95
    Activations Density 0.000%

    No Known Activations