© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 64448
    Prev
    Next
    INDEX
    Explanations

    legal and governmental situations

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

    The neuron lights up on discourse‐level connectives and reporting/action verbs (e.g. “doing,” “decided,” em-dashes, “It’s”) that structure or comment on the flow of speech.

    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
     not
    -1.27
     While
    -1.02
     Despite
    -0.96
    er
    -0.96
     Please
    -0.96
     L
    -0.91
     due
    -0.91
     tiek
    -0.90
     pembangunan
    -0.89
     leonardo
    -0.89
    POSITIVE LOGITS
     But
    1.30
     그리고
    1.27
     another
    1.27
     nastro
    1.25
     другой
    1.23
    但是
    1.21
     אבל
    1.20
     Herramientas
    1.20
    Interviewer
    1.20
     exklu
    1.19
    Activations Density 0.003%

    No Known Activations