© 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. 23396
    Prev
    Next
    INDEX
    Explanations

    medical conditions

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

    widely considered, self-care, risk opening

    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
     기본적인
    0.42
     也
    0.38
    することも
    0.38
    츨
    0.38
    Ⴌ
    0.37
    䀖
    0.36
     \\..
    0.36
    también
    0.35
     ಇತರ
    0.35
    斻
    0.35
    POSITIVE LOGITS
     tinnitus
    0.42
     kanker
    0.41
     PTSD
    0.41
     dyslex
    0.40
     cocaine
    0.40
     disinfectant
    0.39
     chemotherapy
    0.39
     Botox
    0.38
     Ebola
    0.38
     concussion
    0.38
    Activations Density 0.309%

    No Known Activations