© 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. 92284
    Prev
    Next
    INDEX
    Explanations

    notes, warnings, questions

    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
     and
    -1.46
     of
    -1.00
     héroes
    -0.99
    ίων
    -0.96
    பெ
    -0.94
    atherapy
    -0.94
    RODUCTION
    -0.93
     открыть
    -0.92
    ixante
    -0.91
    金钱
    -0.91
    POSITIVE LOGITS
    :
    2.83
    !
    1.88
    !!
    1.26
    Though
    1.23
    !!!
    1.20
    Although
    1.14
     SOBRE
    1.11
    Even
    1.01
    While
    1.01
     regarding
    1.01
    Activations Density 0.050%

    No Known Activations