© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83250
    Prev
    Next
    INDEX
    Explanations

    document metadata

    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
     之
    -0.69
    ред
    -0.67
    OnAdd
    -0.66
    桩
    -0.66
    гер
    -0.66
    协会
    -0.66
     Flughafen
    -0.65
     involuntary
    -0.65
    겠
    -0.65
    AL
    -0.64
    POSITIVE LOGITS
    telo
    0.66
    ISODE
    0.66
     models
    0.65
     bouquets
    0.65
    cée
    0.65
     Marsden
    0.65
    Comer
    0.64
    central
    0.64
    modeling
    0.64
     חלק
    0.64
    Activations Density 0.080%

    No Known Activations