© 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. 115570
    Prev
    Next
    INDEX
    Explanations

    IRS or CAP

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

    cosmic consciousness, search intent

    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
     altid
    0.47
     spez
    0.45
    的作用
    0.45
    نى
    0.44
     selben
    0.43
    สัก
    0.43
    就算
    0.43
    淍
    0.42
     જોઈએ
    0.42
    ถม
    0.42
    POSITIVE LOGITS
     tragic
    0.47
     neon
    0.46
     Bu
    0.46
     cost
    0.45
    expensive
    0.45
     secreted
    0.44
     stadium
    0.44
     प्रकाश
    0.43
     Neon
    0.43
     sensational
    0.42
    Activations Density 0.001%

    No Known Activations