© 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. 92142
    Prev
    Next
    INDEX
    Explanations

    life events and circumstances

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

    violence, prejudice, or abuse

    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
    :
    0.47
    专注于
    0.45
    ,
    0.44
    ati
    0.44
    ór
    0.43
    ē
    0.43
    jø
    0.43
    🛖
    0.43
    øst
    0.42
    ͜
    0.42
    POSITIVE LOGITS
     sogar
    0.52
     eigenlijk
    0.48
     internas
    0.47
    なんと
    0.47
     hijas
    0.46
     craziness
    0.45
     anaknya
    0.43
     cima
    0.43
     printr
    0.43
     bitcoins
    0.43
    Activations Density 0.000%

    No Known Activations