© 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. 34-GEMMASCOPE-RES-131K
    7. 57842
    Prev
    Next
    INDEX
    Explanations

    identifiers and related values

    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
     its
    -1.48
     what
    -1.18
    itename
    -0.99
     пальто
    -0.96
     Donnerstag
    -0.96
     映
    -0.96
     where
    -0.96
     From
    -0.91
     onsdag
    -0.90
     Arxivat
    -0.89
    POSITIVE LOGITS
    ceous
    1.20
     ansik
    1.20
    お花
    1.19
    ,
    1.19
     間取り
    1.15
    atization
    1.13
    ulite
    1.07
    馓
    1.07
     воспомина
    1.07
     céramique
    1.05
    Activations Density 0.056%

    No Known Activations