© 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. 58417
    Prev
    Next
    INDEX
    Explanations

    increase number, for excellence, with inmates

    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
    opie
    -1.39
    ihnachts
    -1.34
     eccl
    -1.33
     appris
    -1.30
     entren
    -1.29
    antaranya
    -1.27
     menganggap
    -1.25
    wants
    -1.21
    ihnachten
    -1.20
    iress
    -1.19
    POSITIVE LOGITS
     program
    1.75
     campus
    1.69
     community
    1.68
     student
    1.68
     project
    1.62
     our
    1.56
     students
    1.53
     school
    1.47
     district
    1.43
     staff
    1.42
    Activations Density 0.223%

    No Known Activations