Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110337
    Prev
    Next
    INDEX
    Explanations

    trying to do something

    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
    轻易
    -1.34
    easily
    -1.25
    Easily
    -1.09
    リスク
    -1.09
     poter
    -1.09
     ability
    -1.09
    試試
    -1.08
     vilja
    -1.08
    Able
    -1.07
    odotus
    -1.05
    POSITIVE LOGITS
     find
    1.52
     figure
    1.47
     get
    1.34
     understand
    1.25
     desesper
    1.08
    汲
    1.07
     decipher
    1.07
     explain
    1.03
     convince
    1.02
     найти
    1.01
    Activations Density 0.080%

    No Known Activations