© 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. 2597
    Prev
    Next
    INDEX
    Explanations

    spread, pour, remove

    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
     délais
    -0.82
    YYY
    -0.82
     quelli
    -0.75
     zilver
    -0.75
    𝑿
    -0.74
    去了
    -0.73
     kèm
    -0.73
     dizaines
    -0.73
     pamoja
    -0.73
     fenêtres
    -0.73
    POSITIVE LOGITS
     spread
    1.35
     poured
    1.24
    Spread
    1.23
     Spread
    1.20
     spreading
    1.19
     pour
    1.17
     pouring
    1.13
     spoon
    1.13
    Pour
    1.07
    แบ
    1.01
    Activations Density 0.011%

    No Known Activations