© 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. 93238
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
     by
    -2.13
    тися
    -2.09
    は
    -2.06
    Beskrivning
    -2.00
    ции
    -1.86
    The
    -1.85
    توضیحات
    -1.81
    饅
    -1.80
     Those
    -1.79
     slight
    -1.76
    POSITIVE LOGITS
    튿
    2.06
    sandalia
    2.05
    耵
    1.98
    ’
    1.89
     keo
    1.88
     meravigli
    1.85
    塍
    1.84
    _
    1.84
    휀
    1.84
     insanely
    1.81
    Activations Density 0.009%

    No Known Activations