© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7576
    Prev
    Next
    INDEX
    Explanations

    sound and noise descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ęcz
    0.73
     കിട
    0.72
    żliw
    0.68
    ক্টো
    0.67
     मझ
    0.67
     हेमा
    0.67
    CoA
    0.66
    渶
    0.66
    zien
    0.65
    zględ
    0.64
    POSITIVE LOGITS
     noises
    2.61
     sounds
    2.56
     noise
    2.43
     louder
    2.37
     sound
    2.36
     audible
    2.34
     звук
    2.33
     sonidos
    2.33
     loud
    2.29
    声音
    2.23
    Activations Density 0.520%

    No Known Activations