© 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. 10-GEMMASCOPE-RES-131K
    7. 65354
    Prev
    Next
    INDEX
    Explanations

    rural, energy, evidence, time, identification

    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_10/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
    </em>
    -1.84
    .
    -1.84
    t
    -1.54
    v
    -1.52
    ar
    -1.51
    no
    -1.51
    o
    -1.50
    單位
    -1.48
    機關
    -1.43
     découv
    -1.41
    POSITIVE LOGITS
    AfterViewInit
    1.70
     THOSE
    1.63
     hermosos
    1.59
     verdaderos
    1.56
    DateFormatter
    1.52
     instrumentos
    1.51
     với
    1.51
    tifying
    1.50
     bocetos
    1.50
    cosse
    1.49
    Activations Density 0.040%

    No Known Activations