© 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. 91645
    Prev
    Next
    INDEX
    Explanations

    use case scenarios

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

    The neuron detects discussion of “use” or “use-case” contexts—that is, when the text is talking about how something is used or what its use case is.

    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
    tissa
    -0.90
    ķ
    -0.86
    Interventions
    -0.86
    ınt
    -0.82
    Джере
    -0.82
    細節
    -0.81
    vox
    -0.80
    ֮
    -0.79
    дется
    -0.79
    ielo
    -0.79
    POSITIVE LOGITS
     scenario
    3.45
     scenarios
    3.44
    scenario
    2.63
    scenarios
    2.58
    Scenario
    2.58
    场景
    2.55
     Scenarios
    2.55
     Scenario
    2.53
     situations
    2.33
     situation
    2.16
    Activations Density 0.229%

    No Known Activations