© 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. 130216
    Prev
    Next
    INDEX
    Explanations

    technical terms and prefixes

    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
    мне
    -1.15
    worden
    -1.05
     geheim
    -1.03
    bakter
    -1.02
     ПК
    -1.02
    соеди
    -1.01
    Ù
    -0.98
     zgodnie
    -0.96
     kropp
    -0.95
     orsz
    -0.95
    POSITIVE LOGITS
     vermutlich
    1.30
     Unterscheidung
    1.18
     controllare
    1.16
    それにしても
    1.16
     zahlreiche
    1.15
     lutar
    1.15
    ちなみに
    1.13
    与此同时
    1.13
    それも
    1.11
    それに
    1.10
    Activations Density 0.000%

    No Known Activations