© 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. 22-GEMMASCOPE-RES-131K
    7. 9830
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases

    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_22/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
     geeigne
    -1.44
     läßt
    -1.35
     ottim
    -1.23
     readily
    -1.23
     heretofore
    -1.22
    supplied
    -1.22
    莚
    -1.20
     keineswegs
    -1.20
    Modell
    -1.19
     erzielt
    -1.19
    POSITIVE LOGITS
    </strong>
    1.25
    л
    1.23
    呦
    1.16
    ка
    1.15
     وبعد
    1.14
     curated
    1.14
     хра
    1.13
    Thankfully
    1.13
     Ре
    1.12
     shitty
    1.12
    Activations Density 0.097%

    No Known Activations