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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 63189
    Prev
    Next
    INDEX
    Explanations

    hammer

    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_all/layer_41_width_262k_l0_big
    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
     sécrétion
    0.41
    CUT
    0.39
    切れ
    0.39
    籃
    0.38
     scrub
    0.38
     incub
    0.37
    ี้ย
    0.37
     داله
    0.37
    ക്കേ
    0.37
    সন্ধ
    0.36
    POSITIVE LOGITS
     hammer
    1.92
     hammers
    1.73
    Hammer
    1.70
     Hammer
    1.66
     hammering
    1.54
     hammered
    1.53
    hammer
    1.51
    锤
    1.45
     Hammers
    1.41
    鎚
    1.22
    Activations Density 0.005%

    No Known Activations