© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78346
    Prev
    Next
    INDEX
    Explanations

    gratitude for actions or support

    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
     would
    -1.04
    即可
    -0.90
     fully
    -0.88
    ној
    -0.85
     возгла
    -0.85
    REL
    -0.84
     Ple
    -0.84
     major
    -0.81
     can
    -0.81
    𝐈
    -0.80
    POSITIVE LOGITS
     support
    1.88
     contributed
    1.80
     contribute
    1.52
     helped
    1.50
     supporting
    1.48
    支持
    1.44
    的支持
    1.43
    support
    1.41
     destek
    1.39
    のおかげ
    1.38
    Activations Density 0.030%

    No Known Activations