© 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. 34-GEMMASCOPE-RES-131K
    7. 102409
    Prev
    Next
    INDEX
    Explanations

    horns and warning sounds

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

    The neuron detects words that denote loud noises or sound‐producing actions and devices (e.g. honking, beep, siren, horn).

    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
     verre
    -0.71
     Philo
    -0.71
    änen
    -0.68
    phate
    -0.68
     nucleotides
    -0.67
    iomanip
    -0.67
     Schwe
    -0.67
    ściu
    -0.66
    phosphate
    -0.66
    namespaces
    -0.66
    POSITIVE LOGITS
     hon
    4.28
     horn
    4.13
     horns
    3.58
    horn
    2.98
     Horn
    2.98
    Horn
    2.88
     Hon
    2.78
     HORN
    2.73
    hon
    2.64
    Hon
    2.56
    Activations Density 0.032%

    No Known Activations