© 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. 69421
    Prev
    Next
    INDEX
    Explanations

    n/a or -

    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
     Diſ
    -1.27
    𓇼
    -1.26
     legjobb
    -1.23
     дуже
    -1.20
    strawberry
    -1.20
    waniem
    -1.20
     umożli
    -1.19
     вже
    -1.19
    lossing
    -1.18
    夕方
    -1.16
    POSITIVE LOGITS
    一是
    1.32
     there
    1.23
    ：“……”
    1.20
    从中
    1.18
    ḿ
    1.16
     except
    1.16
    ToUser
    1.16
    falls
    1.15
    ains
    1.15
     unless
    1.14
    Activations Density 0.033%

    No Known Activations