© 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. 36474
    Prev
    Next
    INDEX
    Explanations

    level, grade, or rating

    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
    I
    -0.88
    €.
    -0.87
    Sr
    -0.85
    tie
    -0.85
    ei
    -0.84
     EDITORIAL
    -0.84
    l
    -0.83
    ;
    -0.83
     from
    -0.82
    yev
    -0.82
    POSITIVE LOGITS
     level
    1.44
    級
    1.32
    level
    1.11
    级
    1.10
     russes
    1.09
     religieuses
    1.08
     уровень
    1.07
     levels
    1.03
     berkunjung
    0.99
     rating
    0.98
    Activations Density 0.171%

    No Known Activations