© 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. 145147
    Prev
    Next
    INDEX
    Explanations

    EVOLUTION, gospel, practice therapy

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

    shared interests and goals

    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
    monium
    0.52
    緩和
    0.51
    ssel
    0.48
    weet
    0.47
    醂
    0.47
    niem
    0.46
    賀
    0.46
    dat
    0.45
     عليها
    0.44
    flamingo
    0.44
    POSITIVE LOGITS
    یدی
    0.51
     snatched
    0.47
    Спољашње
    0.47
    έσ
    0.46
     effectually
    0.42
     hailing
    0.41
     stabilizes
    0.41
     effectual
    0.41
    긴
    0.41
     whi
    0.40
    Activations Density 0.001%

    No Known Activations