© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 182835
    Prev
    Next
    INDEX
    Explanations

    nexus mods, requiring advice, sealed seams

    np_acts-logits-general · gemini-2.5-flash-lite

    literature review and historical analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =\{
    0.50
    屯
    0.46
    sage
    0.45
    乐观
    0.44
    运算
    0.44
    heen
    0.44
    集合
    0.44
    java
    0.43
    góc
    0.43
    h
    0.43
    POSITIVE LOGITS
     slabs
    0.45
     favors
    0.45
     động
    0.42
     নিজের
    0.42
     counterparts
    0.42
     motivos
    0.41
     salaries
    0.41
     coatings
    0.41
     revelar
    0.40
     babies
    0.40
    Activations Density 0.001%

    No Known Activations