© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38812
    Prev
    Next
    INDEX
    Explanations

    German words and English punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on prominent event- or topic-denoting nouns and gerunds (e.g. “firing,” “scheme,” “action,” “problem”) that signal the core happenings in a passage.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     its
    -1.09
    熹
    -0.97
     reinforces
    -0.95
     four
    -0.89
     begrü
    -0.89
     ||
    -0.87
    ("}");
    -0.87
    }$)
    -0.86
     at
    -0.84
     haphazard
    -0.84
    POSITIVE LOGITS
     downloaden
    1.10
    ୪
    1.09
     they
    1.09
     thus
    1.08
    gruppe
    1.01
    sequently
    0.96
    thus
    0.96
     maler
    0.95
    eine
    0.94
     dieser
    0.94
    Activations Density 0.102%

    No Known Activations