© 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. 59503
    Prev
    Next
    INDEX
    Explanations

    detection of

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

    The neuron fires on occurrences of the root “detect” (e.g. detect, detected, detection) in any context.

    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
     noticeable
    -1.13
    x
    -1.13
     Bäume
    -1.09
     doctorate
    -1.09
     seductive
    -1.06
     disconcer
    -1.05
     continual
    -1.04
     unpredic
    -1.04
     nine
    -1.04
     perplexing
    -1.03
    POSITIVE LOGITS
     and
    1.54
     otthon
    1.38
     you
    1.24
     detenidos
    1.19
    zelfde
    1.18
     hosszú
    1.18
    龉
    1.12
     oferece
    1.08
    ША
    1.07
     MANY
    1.06
    Activations Density 0.036%

    No Known Activations