© 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. 69495
    Prev
    Next
    INDEX
    Explanations

    accept major credit cards

    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
    schon
    -1.26
    holde
    -1.23
     Beide
    -1.23
    skaya
    -1.21
    伝え
    -1.20
    Ār
    -1.19
    sieht
    -1.17
     किसी
    -1.16
     اگر
    -1.15
    peka
    -1.15
    POSITIVE LOGITS
     there
    1.73
     what
    1.67
     like
    1.45
     where
    1.32
     how
    1.31
     such
    1.30
     various
    1.23
     why
    1.21
    INTAIN
    1.20
     similar
    1.16
    Activations Density 1.027%

    No Known Activations