© 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. 89940
    Prev
    Next
    INDEX
    Explanations

    experience in context

    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
    ˧
    -1.00
     diminishing
    -0.97
    owi
    -0.97
    𝒫
    -0.94
    zeti
    -0.92
     помещении
    -0.91
    鵙
    -0.91
    𝔽
    -0.88
    echy
    -0.87
    ynku
    -0.87
    POSITIVE LOGITS
     gained
    1.81
     of
    1.56
     in
    1.49
     dealing
    1.30
     and
    1.29
     accumulated
    1.18
     gathered
    1.16
     handling
    1.16
    dealing
    1.05
     with
    1.04
    Activations Density 0.022%

    No Known Activations