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. 3734
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

    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
     Brigadier
    0.80
     Allí
    0.78
     ፣
    0.77
    ,
    0.76
     proguardFiles
    0.72
    انة
    0.72
    6
    0.71
     ،
    0.70
     हैद
    0.70
    ﻯ
    0.70
    POSITIVE LOGITS
     chow
    0.76
    ဘူး
    0.70
    <0xA8>
    0.70
     نهايه
    0.68
    တဲ့
    0.67
    Lew
    0.64
     неви
    0.64
     Pawar
    0.64
    τικού
    0.63
    ㎝
    0.63
    Activations Density 0.317%

    No Known Activations