© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 37307
    Prev
    Next
    INDEX
    Explanations

    forge and blacksmithing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_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
     PAC
    0.39
     Pasta
    0.38
    苜
    0.38
     Pee
    0.38
     yoghurt
    0.37
     frisk
    0.37
     mape
    0.37
     peel
    0.37
     atrop
    0.37
    聿
    0.36
    POSITIVE LOGITS
     forge
    2.83
     forging
    2.67
     forged
    2.52
     Forge
    2.41
    Forge
    2.34
     blacksmith
    2.33
    forge
    2.20
    锻
    2.16
     smith
    1.91
    鍛
    1.91
    Activations Density 0.025%

    No Known Activations