© 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-262K
    7. 220433
    Prev
    Next
    INDEX
    Explanations

    decaying, abandoned, warm, muscular states

    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_262k_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
    勒
    0.44
    Actually
    0.41
     perspective
    0.40
    神
    0.39
     LD
    0.39
     mon
    0.38
     DNA
    0.38
    靼
    0.37
     sunset
    0.37
     six
    0.36
    POSITIVE LOGITS
     объект
    0.44
    sss
    0.43
    qty
    0.41
     सुम
    0.41
     количества
    0.40
    acterium
    0.40
    ukk
    0.40
    数量
    0.40
     ServicePolicy
    0.40
     பின்பற்ற
    0.40
    Activations Density 0.000%

    No Known Activations