© 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. 197118
    Prev
    Next
    INDEX
    Explanations

    ill or death

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

    safety teams, synthetic network, biological perspective

    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
    ऊंगी
    0.51
    ച്ചു
    0.50
    nti
    0.46
     आवंट
    0.46
    reeting
    0.44
     ইলেক
    0.42
     ждать
    0.42
    ⌵
    0.42
    时长
    0.42
    ल्फी
    0.41
    POSITIVE LOGITS
    T
    0.46
    DER
    0.46
    EI
    0.45
    ERROR
    0.45
    H
    0.45
    SSF
    0.45
    SELF
    0.44
    WI
    0.44
    HI
    0.44
     RESPON
    0.44
    Activations Density 0.003%

    No Known Activations