© 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. 10-GEMMASCOPE-RES-131K
    7. 80608
    Prev
    Next
    INDEX
    Explanations

    calling police or authorities

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

    The neuron flags mentions of the police or calling law enforcement.

    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
    '
    -1.24
    Clearing
    -1.19
     וע
    -1.19
     هذه
    -1.16
     rich
    -1.15
     hinten
    -1.14
     usado
    -1.13
    めんな
    -1.12
     %=
    -1.10
    enemies
    -1.09
    POSITIVE LOGITS
    Gemeinsame
    1.35
    PREFERRED
    1.20
    Мекси
    1.16
    ｧ
    1.16
    )":
    1.16
    tiéndose
    1.15
    勠
    1.14
    詎
    1.13
    Анд
    1.13
     how
    1.13
    Activations Density 0.018%

    No Known Activations