© 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. 14088
    Prev
    Next
    INDEX
    Explanations

    appellant v. appellee

    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
     and
    -1.55
    ！（
    -1.16
    …！
    -1.13
    曲は
    -1.10
     árvores
    -1.08
     jugado
    -1.07
    Inggris
    -1.06
    bahasa
    -1.05
     algún
    -1.02
    Gön
    -1.01
    POSITIVE LOGITS
    R
    1.13
    跟著
    1.02
    Ｒ
    1.01
     rigue
    1.01
     prosegu
    1.00
    髋
    0.99
    N
    0.99
    ”？
    0.98
    而非
    0.98
     "--
    0.98
    Activations Density 0.291%

    No Known Activations