© 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. 33962
    Prev
    Next
    INDEX
    Explanations

    mapping to destinations

    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
     fortsatt
    -0.90
    beta
    -0.90
    toBe
    -0.88
     капи
    -0.88
     recomendable
    -0.87
    resizeMode
    -0.87
     članak
    -0.85
     together
    -0.85
    СК
    -0.85
     azért
    -0.84
    POSITIVE LOGITS
     destinations
    1.03
     difficulties
    0.98
     broadening
    0.97
    playstation
    0.96
    色々な
    0.95
     desired
    0.93
     destination
    0.92
    destinations
    0.91
     خارج
    0.90
    ANSA
    0.90
    Activations Density 0.028%

    No Known Activations