© 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. 34-GEMMASCOPE-RES-131K
    7. 116866
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns and articles

    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_34/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
     сначала
    -1.35
    ถ้า
    -1.25
    начала
    -1.23
    首先
    -1.22
    先是
    -1.20
    れば
    -1.10
    ://"
    -1.05
     and
    -1.05
    各有
    -1.02
    ⩽
    -1.02
    POSITIVE LOGITS
     this
    2.83
     these
    2.77
     thus
    2.44
     similar
    2.25
     Thus
    2.16
     therefore
    2.14
     These
    1.91
     overall
    1.91
    Thus
    1.87
     Similar
    1.83
    Activations Density 0.093%

    No Known Activations