© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1219
    Prev
    Next
    INDEX
    Explanations

    small, compact, thin

    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
     taglio
    -0.77
     memberId
    -0.76
    +#+
    -0.74
    rupulous
    -0.74
     TMPro
    -0.74
     variaciones
    -0.73
    akhstan
    -0.72
    )>=
    -0.72
    )+\
    -0.71
     presentan
    -0.71
    POSITIVE LOGITS
     compact
    3.31
    compact
    2.81
    Compact
    2.63
     Compact
    2.55
     footprint
    2.38
     compactness
    2.36
     компакт
    2.31
     size
    2.03
     slim
    2.00
     kompak
    1.97
    Activations Density 0.190%

    No Known Activations