© 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. 39946
    Prev
    Next
    INDEX
    Explanations

    any specified category or condition

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

    This neuron detects the infinitival legal‐statute language that lists prohibited actions (e.g. “to possess,” “to produce,” “to disseminate,” etc.) in laws or regulations.

    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
     colorir
    -1.09
     alcuni
    -1.08
     molti
    -1.06
     เพราะ
    -1.05
     assistir
    -1.02
     ':'
    -1.02
    почка
    -1.02
     muitos
    -0.99
    観て
    -0.96
     our
    -0.94
    POSITIVE LOGITS
     any
    1.60
     or
    1.43
     térmico
    1.32
     specified
    1.28
     magnético
    1.27
     солнца
    1.23
    lemény
    1.22
     expressly
    1.20
     sintético
    1.20
     religiosas
    1.15
    Activations Density 0.079%

    No Known Activations