© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49411
    Prev
    Next
    INDEX
    Explanations

    physical or digital media

    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
    нель
    -0.77
     speaker
    -0.76
    kyo
    -0.74
    nicos
    -0.74
    кация
    -0.72
    nly
    -0.72
    lanted
    -0.71
     fed
    -0.70
    ToTable
    -0.70
     الأرض
    -0.70
    POSITIVE LOGITS
     physical
    1.68
    physical
    1.51
    Physical
    1.48
     Physical
    1.30
     digitally
    1.16
     physically
    1.14
    物理
    1.14
     retail
    1.13
     PHYSICAL
    1.12
     digital
    1.11
    Activations Density 0.040%

    No Known Activations