© 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. 82356
    Prev
    Next
    INDEX
    Explanations

    software components and products

    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
     okuyayım
    -0.84
    шаго
    -0.81
    atellite
    -0.81
     Nach
    -0.80
     مستوى
    -0.77
    gdx
    -0.76
     डे
    -0.75
    Heidelberg
    -0.75
     Noe
    -0.75
    ścia
    -0.75
    POSITIVE LOGITS
     boast
    0.97
    SEVERE
    0.89
     cál
    0.85
    起動
    0.84
    𝕞
    0.84
    陋
    0.82
    giat
    0.82
     fuel
    0.82
    ømme
    0.82
     WORK
    0.81
    Activations Density 0.001%

    No Known Activations