© 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. 48389
    Prev
    Next
    INDEX
    Explanations

    forests and trees

    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
    蛉
    -1.13
     alfalfa
    -1.04
     Alfalfa
    -1.03
    Steg
    -0.90
    ísica
    -0.89
    tuce
    -0.86
     buhay
    -0.85
    ertes
    -0.85
     Venom
    -0.84
    ᚠ
    -0.84
    POSITIVE LOGITS
     forest
    1.30
     stands
    1.26
    林
    1.25
     trees
    1.20
    Forest
    1.15
     younger
    1.13
     dominated
    1.13
     taller
    1.09
     canopy
    1.09
     dominant
    1.09
    Activations Density 0.034%

    No Known Activations