© 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. 19116
    Prev
    Next
    INDEX
    Explanations

    it's [quality]

    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
     Despite
    -2.48
     после
    -2.42
     These
    -2.27
     However
    -2.23
     Giugno
    -2.20
     will
    -2.14
    出来ました
    -2.11
     Luglio
    -2.09
     During
    -2.09
    From
    -2.08
    POSITIVE LOGITS
     renowned
    2.41
    ar
    2.36
    粜
    2.31
     Reſ
    2.31
    秾
    2.25
     been
    2.17
    蟶
    2.14
    creates
    2.06
     lauded
    2.05
     devising
    2.00
    Activations Density 0.096%

    No Known Activations