© 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. 94159
    Prev
    Next
    INDEX
    Explanations

    creating and obtaining

    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
     seems
    -1.06
     Victorian
    -1.04
     came
    -1.02
    able
    -1.01
    されています
    -1.00
     merah
    -0.98
     had
    -0.98
     continual
    -0.98
     two
    -0.94
     four
    -0.92
    POSITIVE LOGITS
    艄
    1.30
    踮
    1.09
     tornando
    1.08
    考えて
    1.05
    the
    1.04
    ATING
    1.03
    </h4>
    1.02
     juntos
    1.02
    悻
    1.01
     considering
    1.00
    Activations Density 0.062%

    No Known Activations