© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 125812
    Prev
    Next
    INDEX
    Explanations

    future actions and consequences

    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
     LEWIS
    0.47
     SOM
    0.46
     Lords
    0.46
    ^{*}(\
    0.44
     Welch
    0.44
     Lewis
    0.43
     PHILLIPS
    0.43
     Phillips
    0.43
     ARCH
    0.42
    ν
    0.42
    POSITIVE LOGITS
    endim
    0.46
    ható
    0.45
     amu
    0.44
    erian
    0.44
    rategy
    0.43
     حياة
    0.43
     vý
    0.43
    ஸ்ட்
    0.43
     उदार
    0.43
    ťaž
    0.43
    Activations Density 0.001%

    No Known Activations