© 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. 22-GEMMASCOPE-RES-131K
    7. 93396
    Prev
    Next
    INDEX
    Explanations

    speaking or asking direct questions

    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_22/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
    tividade
    -0.95
    When
    -0.91
     «
    -0.88
    vara
    -0.85
    RotationOrder
    -0.84
    ższych
    -0.82
    Following
    -0.82
     BigNumberish
    -0.81
    dozen
    -0.81
     termasuk
    -0.81
    POSITIVE LOGITS
     then
    1.13
    yyj
    1.12
     both
    1.05
     their
    1.04
     stessa
    1.02
     galima
    0.98
     ampio
    0.96
    pum
    0.96
     chistes
    0.93
    慳
    0.90
    Activations Density 0.015%

    No Known Activations