© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129532
    Prev
    Next
    INDEX
    Explanations

    start of phrase or sentence

    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
     Whilst
    -1.10
     מקום
    -1.10
    而去
    -1.10
     sometimes
    -1.05
    靱
    -1.02
     might
    -1.01
     their
    -0.99
     may
    -0.99
     muchacho
    -0.98
     twenty
    -0.95
    POSITIVE LOGITS
     you
    1.43
     máte
    1.09
     artificiales
    1.07
    masyarakat
    1.05
     régiment
    0.99
    кумулятор
    0.98
     potete
    0.97
     refroidissement
    0.96
     پنجم
    0.95
    )}=\
    0.95
    Activations Density 0.000%

    No Known Activations