© 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. 23882
    Prev
    Next
    INDEX
    Explanations

    subordinating conjunctions and adverbs

    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
    !
    -1.29
    g
    -1.28
    }
    -1.22
    l
    -1.20
     المياه
    -1.18
    OPSIS
    -1.14
    </h1>
    -1.11
    )
    -1.09
    backslash
    -1.05
    Statut
    -1.04
    POSITIVE LOGITS
    dây
    1.58
    INOIS
    1.55
     jejich
    1.48
     use
    1.43
     CALIFOR
    1.40
    horloge
    1.34
    pirazione
    1.33
     who
    1.31
    phòng
    1.29
     indépendante
    1.29
    Activations Density 0.018%

    No Known Activations