© 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. 183
    Prev
    Next
    INDEX
    Explanations

    the followed by abstract concepts

    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
     for
    -1.74
     during
    -1.59
    étaire
    -1.47
     such
    -1.45
     included
    -1.40
    ah
    -1.40
    am
    -1.38
    二日
    -1.37
    get
    -1.35
     including
    -1.35
    POSITIVE LOGITS
     ceux
    1.63
    ⬮
    1.53
    Galería
    1.53
     Jeden
    1.47
    ADUATE
    1.47
     zarówno
    1.44
    這些
    1.42
    Fernsehserie
    1.41
    
    1.40
     obligé
    1.39
    Activations Density 0.243%

    No Known Activations