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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 166854
    Prev
    Next
    INDEX
    Explanations

    skin as outer protective layer

    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_40_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
     DURING
    0.40
    owers
    0.40
    摷
    0.39
     resonances
    0.39
     surpluses
    0.38
    illier
    0.37
     podczas
    0.37
     energ
    0.37
     சிறப்பாக
    0.37
    礁
    0.37
    POSITIVE LOGITS
    皮肤
    0.68
     skin
    0.66
    Skin
    0.62
    皮膚
    0.61
     피부
    0.58
     SKIN
    0.57
     Skin
    0.56
     त्वचा
    0.56
    skin
    0.55
     skins
    0.52
    Activations Density 0.009%

    No Known Activations