© 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. 12321
    Prev
    Next
    INDEX
    Explanations

    jump

    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
     रासायनिक
    0.45
     დამ
    0.41
    餵
    0.39
     商
    0.39
    เดิน
    0.38
    繚
    0.38
     अल्को
    0.38
    痧
    0.38
     रसायन
    0.37
    ెర
    0.37
    POSITIVE LOGITS
     jumping
    2.95
     jump
    2.77
     jumps
    2.72
     jumped
    2.59
     Jumping
    2.56
    跳
    2.55
     Jump
    2.52
    jump
    2.45
    Jump
    2.45
    jumping
    2.42
    Activations Density 0.039%

    No Known Activations