© 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. 27988
    Prev
    Next
    INDEX
    Explanations

    showing or telling something

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

    This neuron detects words relating to communicating or conveying a message (e.g., send, message, show, tell, signaling).

    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
    Ơ
    -0.98
    Ỷ
    -0.94
    úde
    -0.93
     vinyle
    -0.92
     Betracht
    -0.88
    ğaz
    -0.88
    endimiento
    -0.88
     invá
    -0.87
    ")[
    -0.86
     daraus
    -0.86
    POSITIVE LOGITS
     that
    1.91
     rằng
    1.30
     everybody
    1.13
     everyone
    1.12
     how
    1.10
    зяй
    1.10
     että
    1.08
    anderen
    1.05
     indication
    1.05
     bahwa
    1.05
    Activations Density 0.016%

    No Known Activations