© 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. 10-GEMMASCOPE-RES-131K
    7. 268
    Prev
    Next
    INDEX
    Explanations

    Maven project context

    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_10/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
     graciosas
    -2.63
     tomado
    -2.55
     preciosas
    -2.52
    :"#
    -2.48
     maravillosas
    -2.48
     divertidas
    -2.42
     konus
    -2.36
    :"",
    -2.34
     bellas
    -2.34
    </h5>
    -2.28
    POSITIVE LOGITS
    the
    3.14
    _{
    2.25
    }$
    2.13
    ed
    2.09
    ा
    2.03
    ции
    2.02
     nenhum
    1.95
    a
    1.94
    6
    1.93
     Discussions
    1.92
    Activations Density 0.002%

    No Known Activations