© 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. 51895
    Prev
    Next
    INDEX
    Explanations

    buckle up

    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
    ::~
    0.44
    हू
    0.40
     желания
    0.40
    Lift
    0.39
     насе
    0.38
    MIN
    0.38
     व्हाट
    0.38
    mostat
    0.38
    ˬ
    0.38
    stu
    0.37
    POSITIVE LOGITS
     up
    1.74
     Up
    1.30
    起来
    1.19
    up
    1.18
    Up
    1.11
    起來
    1.10
    ขึ้น
    1.09
     lên
    1.03
     upto
    1.01
    アップ
    1.00
    Activations Density 0.022%

    No Known Activations