© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15802
    Prev
    Next
    INDEX
    Explanations

    nail care and artificial nails

    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
    ստ
    0.48
    鰱
    0.46
     doublet
    0.44
     axiomatic
    0.42
    হাসিক
    0.42
     IEEE
    0.40
    엮
    0.40
    膻
    0.39
     বস্ত্র
    0.39
     Axios
    0.38
    POSITIVE LOGITS
     nail
    1.94
     Nail
    1.80
     nails
    1.80
     Nails
    1.66
    nails
    1.59
    nail
    1.57
     uñas
    1.52
    💅
    1.51
    ネイル
    1.50
     fingern
    1.50
    Activations Density 0.010%

    No Known Activations