© 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. 38292
    Prev
    Next
    INDEX
    Explanations

    prize money and rewards

    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
     Vorles
    -1.31
     work
    -1.19
    etchup
    -1.17
     our
    -1.10
     Unterrichts
    -1.10
     from
    -1.05
     contact
    -1.05
    order
    -1.05
     products
    -1.02
     completed
    -1.02
    POSITIVE LOGITS
     escalier
    1.38
    设立
    1.34
     pouvaient
    1.30
     remun
    1.27
    างเกง
    1.23
    zów
    1.23
     devaient
    1.21
    後で
    1.20
    酝
    1.20
     annoncé
    1.15
    Activations Density 0.012%

    No Known Activations