© 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. 34510
    Prev
    Next
    INDEX
    Explanations

    numbers followed by "years"

    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
     things
    -0.94
    Things
    -0.85
    正如
    -0.76
     argument
    -0.74
    相同
    -0.73
     qualquer
    -0.73
     полно
    -0.72
    いただけます
    -0.71
    Enc
    -0.71
    jecture
    -0.71
    POSITIVE LOGITS
    uropa
    0.90
    ⤴
    0.82
    Hoa
    0.81
    ऽ
    0.78
    Ukra
    0.78
     HOC
    0.77
     cheddar
    0.77
     NAVIGATION
    0.77
    vertreter
    0.76
    clutch
    0.75
    Activations Density 0.013%

    No Known Activations