© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53612
    Prev
    Next
    INDEX
    Explanations

    transfer, transmit, convey

    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_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
    rugg
    0.65
    ipset
    0.59
    om
    0.55
    ्रा
    0.55
    ry
    0.54
    ying
    0.53
    य
    0.53
    ari
    0.51
    }=\
    0.50
    umbling
    0.50
    POSITIVE LOGITS
     переда
    1.28
     transfer
    1.16
     전달
    1.15
     transmit
    1.12
    Transfer
    1.06
     передачи
    1.06
    传递
    1.05
    transfer
    1.04
    伝え
    1.01
     transmite
    1.00
    Activations Density 0.061%

    No Known Activations