© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84441
    Prev
    Next
    INDEX
    Explanations

    everything you/to/from

    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
     avevano
    -1.20
    🔷
    -1.14
     contribución
    -1.10
    kwür
    -1.09
     există
    -1.07
    hehehe
    -1.06
    лись
    -1.05
    젝
    -1.04
    llavero
    -1.03
     toilettes
    -1.03
    POSITIVE LOGITS
     that
    1.61
     while
    1.38
     from
    1.34
     could
    1.33
     to
    1.29
     you
    1.27
     they
    1.13
     imaginable
    1.11
     on
    1.10
     one
    1.10
    Activations Density 0.022%

    No Known Activations