© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118075
    Prev
    Next
    INDEX
    Explanations

    plain

    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
    ≼
    -0.91
    tigkeit
    -0.79
     proiz
    -0.79
    ්‍ර
    -0.75
    DatabaseError
    -0.75
     proximité
    -0.75
    ütter
    -0.74
    𝜔
    -0.72
     pertence
    -0.72
    ্দ
    -0.72
    POSITIVE LOGITS
     plain
    4.63
    plain
    3.81
     Plain
    3.55
    Plain
    3.52
    PLAIN
    2.92
     bare
    2.83
     naked
    2.44
     simple
    2.42
     basic
    2.30
     pure
    2.27
    Activations Density 0.112%

    No Known Activations