© 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. 71110
    Prev
    Next
    INDEX
    Explanations

    adding information

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

    The neuron fires on sentence‐level “signpost” words—especially discourse adverbs (e.g. “Additionally,” “Also”) and reporting cues in news text.

    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
     wirklich
    -1.06
     especially
    -1.05
     eventually
    -1.03
     potem
    -0.96
     mainly
    -0.94
    чают
    -0.93
     často
    -0.93
     puțin
    -0.92
     ultimately
    -0.91
     really
    -0.90
    POSITIVE LOGITS
     also
    3.03
     também
    2.20
    Also
    2.13
     также
    2.11
     también
    2.09
    also
    1.88
     ALSO
    1.81
    también
    1.79
     també
    1.78
     También
    1.77
    Activations Density 0.079%

    No Known Activations