© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15293
    Prev
    Next
    INDEX
    Explanations

    alarm sounds

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    糯
    0.58
     Caball
    0.57
     Junius
    0.56
     driftwood
    0.53
    ർ
    0.52
    getAbsolutePath
    0.52
     CANVAS
    0.52
     throughput
    0.51
    槎
    0.51
     হাব
    0.50
    POSITIVE LOGITS
     alarm
    2.81
     alarms
    2.70
    alarm
    2.64
     Alarm
    2.61
    Alarm
    2.53
     alarma
    2.31
     buzzer
    2.16
     bells
    2.13
     siren
    2.08
     sirens
    2.00
    Activations Density 0.111%

    No Known Activations