© 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. 63133
    Prev
    Next
    INDEX
    Explanations

    old

    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
     líquidos
    -0.91
     erläut
    -0.89
    endous
    -0.86
    énier
    -0.86
     decisão
    -0.83
     crecer
    -0.82
     labeled
    -0.81
    🦽
    -0.81
    olving
    -0.81
    spes
    -0.81
    POSITIVE LOGITS
     still
    1.54
     قدیمی
    1.31
     adage
    1.22
     from
    1.11
     now
    1.10
     old
    1.09
     dating
    1.07
    fashioned
    1.06
    still
    1.02
     vẫn
    1.02
    Activations Density 0.046%

    No Known Activations