© 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. 99842
    Prev
    Next
    INDEX
    Explanations

    conflict escalation worse situation

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

    The neuron lights up on words that signal potential threats or negative outcomes—terms used to introduce warnings or risks (e.g. fear, could, bloody, conflict, unchecked).

    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
    sometimes
    -1.28
     nästan
    -1.13
    often
    -1.13
     frequentemente
    -1.09
     senaste
    -1.09
     ibland
    -1.06
     sometimes
    -1.04
     spesso
    -1.02
     často
    -1.02
    ˶
    -1.01
    POSITIVE LOGITS
     another
    1.55
     further
    1.50
     major
    1.18
     a
    1.15
     повто
    1.13
     repeats
    1.10
     escenario
    1.09
     worse
    1.08
     scenario
    1.07
     repeat
    1.06
    Activations Density 0.064%

    No Known Activations