© 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. 22-GEMMASCOPE-RES-131K
    7. 72723
    Prev
    Next
    INDEX
    Explanations

    author and date metadata

    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
    ХОД
    -1.05
     ingrat
    -1.02
     should
    -1.00
    łać
    -0.93
    ůž
    -0.92
    🥴
    -0.92
    iligt
    -0.92
    ellón
    -0.92
     any
    -0.91
     Congreg
    -0.91
    POSITIVE LOGITS
     student
    1.60
     students
    1.27
     college
    1.27
     Tuesday
    1.14
     Saturday
    1.14
     school
    1.11
     Sunday
    1.08
     estudiante
    1.07
     снимка
    1.07
     Student
    1.07
    Activations Density 0.010%

    No Known Activations