Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1476
    Prev
    Next
    INDEX
    Explanations

    monotone voice

    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_29_width_65k_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
     окна
    0.69
     곱
    0.66
     Correlation
    0.65
    cyclo
    0.65
     රස
    0.65
    AcOH
    0.65
    டுகளில்
    0.64
    ంబ
    0.64
     工程
    0.64
    馋
    0.64
    POSITIVE LOGITS
     speech
    3.37
     speaking
    3.25
     speak
    3.09
     speeches
    3.01
     Speech
    3.00
    Speech
    2.92
     spoken
    2.82
    speech
    2.80
     Speaking
    2.77
    speaking
    2.74
    Activations Density 0.826%

    No Known Activations