© 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. 61997
    Prev
    Next
    INDEX
    Explanations

    bridge, role, action, redundancy

    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
    ਵੇ
    0.46
     вече
    0.44
    死
    0.44
     устройства
    0.43
    混
    0.43
    ער
    0.42
    定
    0.42
    ков
    0.42
     безопас
    0.42
     死
    0.42
    POSITIVE LOGITS
     chose
    0.47
     chosen
    0.46
     contacted
    0.46
     downloaded
    0.46
     besi
    0.46
     jurisdiction
    0.45
     chiếc
    0.44
     provider
    0.44
     Curve
    0.43
     watched
    0.43
    Activations Density 0.001%

    No Known Activations