© 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. 128291
    Prev
    Next
    INDEX
    Explanations

    location or inclusion within contexts

    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
    amir
    -0.98
     nivå
    -0.92
    uva
    -0.90
    ➦
    -0.90
    fand
    -0.89
    фи
    -0.88
    ofte
    -0.88
     betale
    -0.85
     Beek
    -0.85
    olester
    -0.84
    POSITIVE LOGITS
     everything
    1.05
    coltà
    1.02
     activities
    0.95
     these
    0.92
     Betrach
    0.92
     Gemü
    0.87
     some
    0.87
     things
    0.86
     this
    0.86
    معرفی
    0.84
    Activations Density 0.109%

    No Known Activations