© 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. 65798
    Prev
    Next
    INDEX
    Explanations

    renowned, employed, assured

    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
    styleUrls
    -0.88
     compagnon
    -0.86
    zwei
    -0.84
     palestra
    -0.84
    Controle
    -0.83
    வி
    -0.82
    お部屋
    -0.82
     Decre
    -0.81
    <bos>
    -0.81
     Прези
    -0.81
    POSITIVE LOGITS
     pentru
    0.94
     gjø
    0.90
     "</
    0.90
    ("^
    0.89
    +".
    0.88
    MENAFN
    0.88
     frecuentes
    0.87
    (_
    0.86
    (["
    0.85
    odon
    0.84
    Activations Density 0.008%

    No Known Activations