© 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. 40-GEMMASCOPE-2-RES-65K
    7. 50170
    Prev
    Next
    INDEX
    Explanations

    tenancy, tenure, or have

    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
    VERSION
    0.40
    エ
    0.40
    케
    0.40
    Ι
    0.40
    তামূলক
    0.39
     처
    0.39
    во
    0.38
    처
    0.38
     instructs
    0.37
    станции
    0.37
    POSITIVE LOGITS
     тен
    0.49
     تن
    0.47
    acité
    0.46
     Тен
    0.44
     tenancy
    0.43
     prinsip
    0.40
     princip
    0.40
     tenue
    0.39
     قدر
    0.38
     Multiplayer
    0.38
    Activations Density 0.015%

    No Known Activations