© 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. 266
    Prev
    Next
    INDEX
    Explanations

    on followed by a noun

    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
     今
    -1.04
    这意味着
    -0.87
     artwork
    -0.85
     aastal
    -0.84
    Matching
    -0.83
    …。
    -0.83
    />
    -0.82
     =
    -0.82
    を
    -0.79
    e
    -0.78
    POSITIVE LOGITS
     behalf
    1.13
     basis
    1.12
     anvil
    1.06
     priority
    1.02
    を探す
    0.93
     sidelines
    0.93
     pretext
    0.92
    にします
    0.90
    所に
    0.88
    sponge
    0.87
    Activations Density 0.030%

    No Known Activations