© 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. 15625
    Prev
    Next
    INDEX
    Explanations

    game context

    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
     traged
    -1.31
    ଂ
    -1.24
     Bakan
    -1.22
     pikachu
    -1.21
     Fakta
    -1.16
     Kategor
    -1.13
    年には
    -1.13
     السياس
    -1.13
     kaos
    -1.12
     golem
    -1.12
    POSITIVE LOGITS
    item
    1.21
    。
    1.09
     режим
    1.08
     each
    1.07
    ïd
    1.03
     you
    1.02
     możliwość
    1.00
     level
    1.00
     storyline
    1.00
     during
    0.99
    Activations Density 0.025%

    No Known Activations