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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41222
    Prev
    Next
    INDEX
    Explanations

    romani, romaine, romania, romero

    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
    レンチ
    0.83
    帶
    0.80
     Limit
    0.79
    带
    0.79
    吨
    0.77
     गं
    0.76
    𒁉
    0.75
     wrist
    0.75
    ข
    0.75
     送料
    0.75
    POSITIVE LOGITS
    ual
    0.96
    UAL
    0.83
    âne
    0.83
     паз
    0.81
     total
    0.77
     general
    0.76
    Ane
    0.74
    ney
    0.74
     Wasn
    0.74
     ताज
    0.74
    Activations Density 0.005%

    No Known Activations