© 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. 20515
    Prev
    Next
    INDEX
    Explanations

    comparison or alternative

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

    beneficial or harmful conjunctions

    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
    Einzel
    0.51
    Puede
    0.46
    Portada
    0.45
    ്‍
    0.44
    Even
    0.44
    מ
    0.44
    นอก
    0.43
    Wallpaper
    0.43
    𝟭
    0.43
    antes
    0.42
    POSITIVE LOGITS
     selects
    0.48
     exclusively
    0.47
     subgroups
    0.46
     inmig
    0.44
     routinely
    0.43
     electing
    0.43
     enroll
    0.42
     substituents
    0.42
     trustee
    0.41
     nuns
    0.41
    Activations Density 0.003%

    No Known Activations