© 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. 216908
    Prev
    Next
    INDEX
    Explanations

    state tax

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

    facts vs opinions

    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
     teard
    0.52
     women
    0.51
     Women
    0.48
     Stal
    0.46
     Dado
    0.45
    -
    0.45
     Czech
    0.45
     heck
    0.44
     message
    0.44
     rail
    0.43
    POSITIVE LOGITS
    𝐩
    0.65
    操作系统
    0.60
     khử
    0.60
    𝐓
    0.57
     ხელისუფლების
    0.55
    }^{+}\
    0.54
    oglobine
    0.53
    𝘥
    0.53
    𝐖
    0.53
     يقوم
    0.53
    Activations Density 0.000%

    No Known Activations