© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57245
    Prev
    Next
    INDEX
    Explanations

    special guests

    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
     organizers
    -0.85
    configurable
    -0.79
    rillation
    -0.76
    𝑦
    -0.76
     עי
    -0.75
     organisers
    -0.73
    beiten
    -0.73
    شنامه
    -0.71
    στά
    -0.70
     وتسجيلات
    -0.70
    POSITIVE LOGITS
     guests
    7.34
     guest
    6.09
     Guests
    5.44
    Guests
    5.41
    guests
    5.09
    guest
    4.78
     Guest
    4.44
    Guest
    4.41
     GUEST
    4.34
    GUEST
    4.06
    Activations Density 0.068%

    No Known Activations