© 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. 19306
    Prev
    Next
    INDEX
    Explanations

    will be + verb/adjective

    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
     gethan
    -1.71
     its
    -1.58
    cembre
    -1.57
     itself
    -1.57
    れてる
    -1.52
    けます
    -1.49
     każdy
    -1.47
    搋
    -1.45
     wła
    -1.44
    嬸
    -1.43
    POSITIVE LOGITS
     only
    1.50
    𓐍
    1.41
    </h1>
    1.38
    žit
    1.38
    Более
    1.37
     tikai
    1.35
    Only
    1.30
    </h2>
    1.28
    licante
    1.24
    subsection
    1.23
    Activations Density 0.013%

    No Known Activations