© 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. 59263
    Prev
    Next
    INDEX
    Explanations

    during or in

    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
    と
    -1.24
    <bos>
    -1.16
    など
    -1.11
    ald
    -1.08
    は
    -1.05
    でも
    -1.05
    を
    -1.05
    や
    -1.04
    にも
    -1.02
    などの
    -1.01
    POSITIVE LOGITS
     while
    1.63
     this
    1.28
     throughout
    1.20
     within
    1.13
    過程中
    1.13
     that
    1.10
    んですね
    1.08
     during
    1.03
     beneath
    1.03
     most
    1.02
    Activations Density 0.000%

    No Known Activations