© 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. 31-GEMMASCOPE-2-RES-65K
    7. 29012
    Prev
    Next
    INDEX
    Explanations

    specific nouns and concepts

    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
     ведь
    0.53
     дома
    0.46
    𝑵
    0.44
     Infantil
    0.44
     Бы
    0.44
     dibuka
    0.44
     сне
    0.43
    е
    0.43
    anc
    0.43
     топлива
    0.43
    POSITIVE LOGITS
    ಂದು
    0.45
    زء
    0.41
    ¸
    0.39
     regalo
    0.38
    طلق
    0.37
     moy
    0.37
     função
    0.36
     relates
    0.35
     guad
    0.35
    ltk
    0.35
    Activations Density 0.002%

    No Known Activations