© 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. 5473
    Prev
    Next
    INDEX
    Explanations

    more about

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

    moral distress

    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
    Contributor
    0.43
    芢
    0.40
    缫
    0.40
     campaigns
    0.39
    Pep
    0.39
     паспо
    0.39
    映射
    0.39
    Additional
    0.38
    结合
    0.38
    韭
    0.37
    POSITIVE LOGITS
    elt
    0.41
     satisfactor
    0.39
    traf
    0.39
    .'”
    0.39
    .?
    0.38
     brim
    0.38
    そうだ
    0.38
     stayed
    0.38
     sunday
    0.38
    iya
    0.38
    Activations Density 0.000%

    No Known Activations