© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64344
    Prev
    Next
    INDEX
    Explanations

    not

    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
     zowel
    -1.40
     either
    -1.30
     навіть
    -1.27
     semplicemente
    -1.25
     simplement
    -1.23
     sogenannte
    -1.23
    BOTH
    -1.23
     либо
    -1.21
     simply
    -1.20
     simplemente
    -1.16
    POSITIVE LOGITS
     directly
    1.98
    直接
    1.97
     exactly
    1.63
     непосредственно
    1.60
     explicitly
    1.57
    directly
    1.55
     exact
    1.53
     direkte
    1.46
     přímo
    1.39
     direkt
    1.35
    Activations Density 0.042%

    No Known Activations