© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 714
    Prev
    Next
    INDEX
    Explanations

    y = or y(

    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
    FFICIENT
    -1.43
    ężczy
    -1.38
    lovakia
    -1.37
    Ꙭ
    -1.33
     tehn
    -1.33
    Medien
    -1.33
    𝘆
    -1.32
    some
    -1.31
    嗬
    -1.30
    ribue
    -1.29
    POSITIVE LOGITS
    .
    1.40
    :
    1.38
     different
    1.27
    mė
    1.22
     every
    1.20
    '
    1.16
    торая
    1.15
    kjø
    1.14
     缝
    1.14
     стала
    1.14
    Activations Density 0.036%

    No Known Activations