© 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. 57952
    Prev
    Next
    INDEX
    Explanations

    returning output variables

    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
    licopter
    -1.26
     créer
    -1.07
     protéger
    -1.06
    傒
    -1.05
    ⏑
    -1.04
     proteção
    -1.02
    included
    -1.02
    $_.
    -1.01
     réinitial
    -1.00
     diğer
    -1.00
    POSITIVE LOGITS
     it
    1.30
     and
    1.27
    ;
    1.12
    ;
    1.09
     at
    1.07
     in
    0.98
     There
    0.89
     focusing
    0.89
     hoping
    0.88
     while
    0.88
    Activations Density 0.004%

    No Known Activations