© 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. 31-GEMMASCOPE-2-RES-65K
    7. 30497
    Prev
    Next
    INDEX
    Explanations

    movement and transfer

    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
    waitKey
    0.42
     Autobi
    0.38
    ファッション
    0.37
    turbo
    0.36
     bicovariant
    0.35
    ricks
    0.35
     כמ
    0.34
    愷
    0.34
     přímo
    0.34
    koe
    0.33
    POSITIVE LOGITS
     relocated
    1.52
     relocation
    1.50
     relocate
    1.45
     relocating
    1.35
     reloc
    1.34
     옮
    1.33
     przen
    1.27
     переме
    1.26
    移動
    1.24
    转移
    1.23
    Activations Density 0.128%

    No Known Activations