© 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. 75203
    Prev
    Next
    INDEX
    Explanations

    defined as

    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
    ־ה
    -1.01
    但她
    -0.96
     ziel
    -0.90
    她也
    -0.88
    parr
    -0.88
     soprattutto
    -0.86
    ENEF
    -0.86
     cá
    -0.85
     chì
    -0.85
     instead
    -0.84
    POSITIVE LOGITS
     it
    1.45
     нём
    1.04
     éste
    1.04
    它
    0.89
    ilers
    0.86
    شنبه
    0.85
    Located
    0.85
     pantalon
    0.84
    вой
    0.83
     Norwood
    0.83
    Activations Density 0.038%

    No Known Activations