© 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. 34-GEMMASCOPE-RES-131K
    7. 32999
    Prev
    Next
    INDEX
    Explanations

    positive descriptors for choices

    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
     Профиль
    -1.06
    uscht
    -0.98
    jdzie
    -0.96
    схема
    -0.94
    erdings
    -0.93
    Fonto
    -0.93
    utados
    -0.92
    ificato
    -0.92
     amélior
    -0.92
    ArgsConstructor
    -0.91
    POSITIVE LOGITS
     choice
    5.81
     choices
    4.44
    choice
    4.19
     option
    3.77
    Choice
    3.61
     choix
    3.59
     Choice
    3.56
    choices
    3.14
     options
    2.92
     scelta
    2.91
    Activations Density 0.078%

    No Known Activations