© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110655
    Prev
    Next
    INDEX
    Explanations

    long linear material

    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
     kotak
    -0.80
    ૦
    -0.77
    spectos
    -0.74
    spots
    -0.73
     LUB
    -0.71
     Anya
    -0.71
    NodeType
    -0.70
     database
    -0.70
    ိ
    -0.70
     kone
    -0.69
    POSITIVE LOGITS
     wires
    1.95
     cables
    1.79
     cable
    1.74
     strings
    1.67
     wire
    1.66
    strings
    1.55
     rope
    1.53
     strands
    1.48
     string
    1.48
     threads
    1.46
    Activations Density 0.192%

    No Known Activations