© 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. 1933
    Prev
    Next
    INDEX
    Explanations

    density functional

    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
     ewigen
    -1.10
     dunklen
    -1.05
     selben
    -0.97
     Ooh
    -0.94
    öten
    -0.93
     vorigen
    -0.91
     Relatively
    -0.91
     vollen
    -0.91
     reinen
    -0.90
     Yet
    -0.88
    POSITIVE LOGITS
     of
    1.27
     lipoprotein
    1.02
     gradient
    1.02
     polyethylene
    0.90
    ρ
    0.88
    \
    0.86
     julio
    0.85
    垕
    0.84
     arreg
    0.81
    /
    0.81
    Activations Density 0.019%

    No Known Activations