© 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. 91919
    Prev
    Next
    INDEX
    Explanations

    causality or influence

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

    The neuron strongly activates on agent-by phrases (i.e. the preposition “by” and its surrounding words in passive/“driven by…” constructions).

    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
    溝通
    -1.01
    主動
    -0.96
     plaît
    -0.95
    馳
    -0.93
    最为
    -0.93
     vägen
    -0.92
    ありました
    -0.90
     некоторых
    -0.89
    neur
    -0.89
     cabriolet
    -0.88
    POSITIVE LOGITS
     a
    1.73
     factors
    1.59
     considerations
    1.53
     circumstance
    1.47
     the
    1.43
     fear
    1.37
     strong
    1.36
    factors
    1.34
     necessity
    1.28
     something
    1.27
    Activations Density 0.092%

    No Known Activations