© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110601
    Prev
    Next
    INDEX
    Explanations

    what happened or occurred

    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
     is
    -1.16
     dévelo
    -0.93
     案例
    -0.91
     exemples
    -0.91
     épu
    -0.90
     visites
    -0.90
     THINGS
    -0.90
     LUNCH
    -0.89
     ratón
    -0.88
     lavable
    -0.88
    POSITIVE LOGITS
     happened
    3.38
     occurred
    2.50
     transpired
    1.91
     happen
    1.88
     happening
    1.82
     went
    1.72
     occured
    1.64
    發生
    1.50
     occur
    1.48
     Happened
    1.45
    Activations Density 0.022%

    No Known Activations