© 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. 10-GEMMASCOPE-RES-131K
    7. 29073
    Prev
    Next
    INDEX
    Explanations

    Ricci, Amethyst, medley

    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_10/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
    逦
    -2.84
    %;
    -2.70
    裢
    -2.47
     (‘
    -2.44
    媖
    -2.42
    ྜ
    -2.41
    縐
    -2.38
    觔
    -2.31
    与此
    -2.27
    وفير
    -2.27
    POSITIVE LOGITS
    0
    3.72
    4
    3.34
    7
    3.16
    5
    2.84
    6
    2.83
    3
    2.67
    8
    2.63
    鉿
    2.47
    9
    2.47
     they
    2.47
    Activations Density 0.015%

    No Known Activations