© 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. 103483
    Prev
    Next
    INDEX
    Explanations

    The intellectual property

    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
     poté
    -0.84
    shots
    -0.79
    reef
    -0.77
    Msg
    -0.75
     ANZ
    -0.73
     Madhya
    -0.73
     StyleSheet
    -0.72
     окре
    -0.71
    biór
    -0.71
     Via
    -0.70
    POSITIVE LOGITS
     batch
    1.26
    batch
    1.02
     Batch
    1.01
     bénéficie
    0.88
     sample
    0.88
     MOORE
    0.87
    Batch
    0.85
    ttemberg
    0.85
     bat
    0.84
     DECISION
    0.84
    Activations Density 0.002%

    No Known Activations