© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2671
    Prev
    Next
    INDEX
    Explanations

    loud sounds, noises, and voices

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

    sound and noise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
    茛
    0.44
    拈
    0.44
    看完
    0.39
     বলিয়াছেন
    0.39
     حبايبي
    0.38
    ेयर
    0.38
    ңү
    0.37
    sunline
    0.37
     紹介
    0.37
    綑
    0.37
    POSITIVE LOGITS
     loud
    2.78
     noises
    2.69
     louder
    2.69
     noise
    2.63
     loudest
    2.53
     sounds
    2.52
    声音
    2.52
    เสียง
    2.48
     zvuk
    2.41
     sonido
    2.39
    Activations Density 0.533%

    No Known Activations