© 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-16K
    7. 12875
    Prev
    Next
    INDEX
    Explanations

    personal stories about illness and hospitals

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

    hospitalized and medical conditions

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

    hospitalization

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_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
     Bentham
    0.54
    焚
    0.47
    揀
    0.44
     ചൂ
    0.42
    やか
    0.41
    黜
    0.41
     합동
    0.41
     النساء
    0.41
     கொலை
    0.41
     counterclaim
    0.41
    POSITIVE LOGITS
    病情
    0.79
     hospitalization
    0.75
     hospitalized
    0.72
     ICU
    0.70
    住院
    0.70
     prognosis
    0.70
    cancer
    0.66
     hospitals
    0.65
    痊
    0.65
     malattia
    0.65
    Activations Density 0.224%

    No Known Activations