© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69162
    Prev
    Next
    INDEX
    Explanations

    unavailability or lack of something

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

    The neuron flags descriptions of problems or failures—phrases conveying setbacks, errors, or things not working as expected.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     now
    -1.21
     you
    -1.09
    yonel
    -1.04
    现在
    -0.97
     сейчас
    -0.96
    Сейчас
    -0.96
    Clik
    -0.94
    gten
    -0.92
    常常
    -0.90
    ITAS
    -0.90
    POSITIVE LOGITS
     available
    1.45
    ıyordu
    1.20
     offered
    1.11
     so
    1.10
     encontramos
    1.09
    なかったので
    1.06
    だったので
    1.05
     نداشت
    1.03
     hieß
    1.02
     there
    1.01
    Activations Density 0.026%

    No Known Activations