© 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. 40-GEMMASCOPE-2-RES-65K
    7. 2747
    Prev
    Next
    INDEX
    Explanations

    Deep Dive, DeepMind

    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_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
    𝖽
    0.44
    舫
    0.43
    сов
    0.43
    㕵
    0.43
    距
    0.40
    ορ
    0.39
    ltimes
    0.39
    eci
    0.39
     მონ
    0.38
     vistos
    0.38
    POSITIVE LOGITS
     deep
    1.23
     Deep
    1.06
    深
    1.06
    Deep
    1.05
    deep
    1.04
     глубо
    1.04
     깊
    1.03
     profund
    0.93
     deeper
    0.92
     profunda
    0.92
    Activations Density 0.092%

    No Known Activations