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. 41052
    Prev
    Next
    INDEX
    Explanations

    cold water

    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
     decreases
    0.75
    decl
    0.72
     enth
    0.69
    ஐ
    0.68
     감소
    0.65
     ajo
    0.65
     declines
    0.64
     Shr
    0.63
    DECL
    0.62
    स्फ
    0.61
    POSITIVE LOGITS
     سوم
    0.93
    سوم
    0.77
     বিন্দু
    0.74
    ዶች
    0.74
     వైద్య
    0.74
     solicitors
    0.73
     तिस
    0.73
    лих
    0.71
    颇
    0.71
     মিলিয়ন
    0.71
    Activations Density 0.000%

    No Known Activations