© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52035
    Prev
    Next
    INDEX
    Explanations

    goods and property

    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_31_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
     Azerbaijani
    0.41
     Brasileira
    0.41
    ttamente
    0.40
     फुटबल
    0.40
     Bai
    0.39
    ünft
    0.39
    bollywood
    0.39
    멎
    0.38
    inti
    0.38
     fateful
    0.38
    POSITIVE LOGITS
    тара
    0.52
     опла
    0.45
    кру
    0.43
     tarifs
    0.41
     Kommunikation
    0.41
     продав
    0.41
     jour
    0.40
     фотографии
    0.40
     foto
    0.40
     фото
    0.40
    Activations Density 0.022%

    No Known Activations