© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45313
    Prev
    Next
    INDEX
    Explanations

    so quick to

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

    The neuron detects strongly felt emotional or mental states, signaled by intense feeling words (e.g. anxious, traumatized, sickened, crabby).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    I
    -1.59
     blanda
    -1.43
    Koordinaten
    -1.39
    !
    -1.38
    k
    -1.38
     beteiligt
    -1.34
    君は
    -1.34
    na
    -1.34
     nation
    -1.33
     People
    -1.32
    POSITIVE LOGITS
    ліз
    1.50
    閦
    1.44
     or
    1.41
    蚰
    1.39
    หรือ
    1.37
    blestone
    1.34
    vocations
    1.32
    mountable
    1.30
    šenie
    1.29
    gefühl
    1.27
    Activations Density 0.136%

    No Known Activations