© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67299
    Prev
    Next
    INDEX
    Explanations

    demonstrated that

    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
     three
    -1.43
     guerras
    -1.28
     after
    -1.23
     flechas
    -1.23
    OTTEN
    -1.23
     sehr
    -1.23
    taya
    -1.23
     bicicletas
    -1.20
     curvas
    -1.20
     four
    -1.20
    POSITIVE LOGITS
     you
    1.57
     melding
    1.46
     evoc
    1.35
     savag
    1.34
     cruelly
    1.34
    就可以了
    1.32
    Они
    1.29
     implor
    1.28
     unbear
    1.26
     unspeak
    1.23
    Activations Density 0.058%

    No Known Activations