© 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. 34-GEMMASCOPE-RES-131K
    7. 1067
    Prev
    Next
    INDEX
    Explanations

    comes as

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

    This neuron primarily detects news‐style discourse markers and temporal/connective signals (e.g. “comes,” “on,” “announcement,” “proposal,” commas) that structure and transition reporting.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     its
    -1.01
    antwoorde
    -0.99
    ">:
    -0.96
    去年
    -0.91
    jenie
    -0.91
    ṝ
    -0.89
     ſte
    -0.89
    iço
    -0.88
    ctomy
    -0.88
     eventualmente
    -0.86
    POSITIVE LOGITS
     amid
    2.11
     days
    2.02
     just
    1.74
     weeks
    1.67
     días
    1.53
     after
    1.53
     months
    1.48
     nadat
    1.45
     amidst
    1.45
     ahead
    1.36
    Activations Density 0.041%

    No Known Activations