© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2477
    Prev
    Next
    INDEX
    Explanations

    leather and tanning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    ัศ
    0.96
    5
    0.87
    antai
    0.81
    6
    0.80
    owering
    0.79
     Majka
    0.78
    MNOP
    0.76
    ₆
    0.74
     competição
    0.73
    ként
    0.73
    POSITIVE LOGITS
     Leather
    2.71
    leather
    2.62
     leather
    2.59
    Leather
    2.51
    レザー
    2.28
    皮革
    2.06
     レザー
    2.04
     Leder
    1.75
     革
    1.73
     tannins
    1.68
    Activations Density 0.063%

    No Known Activations