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. 41140
    Prev
    Next
    INDEX
    Explanations

    push exercises

    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
    Sole
    0.70
     کاغذ
    0.69
    Lug
    0.68
    Thread
    0.67
     Lug
    0.66
    Walking
    0.66
    俵
    0.65
     hologram
    0.64
    Shuffle
    0.64
     International
    0.63
    POSITIVE LOGITS
     push
    0.90
     dip
    0.83
     Push
    0.83
    KHTML
    0.80
     pull
    0.78
    ರಣ
    0.78
     푸
    0.77
    push
    0.76
     पुश
    0.74
    ahami
    0.73
    Activations Density 0.030%

    No Known Activations