© 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. 101966
    Prev
    Next
    INDEX
    Explanations

    patient health matters

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

    simple subtraction

    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
    ма
    0.47
     шко
    0.46
    știg
    0.44
    ве
    0.44
     Богу
    0.44
    आपको
    0.43
     बचा
    0.43
    с
    0.43
    ка
    0.42
     tin
    0.42
    POSITIVE LOGITS
     pasien
    0.59
     pazienti
    0.56
     paciente
    0.56
     paziente
    0.52
     patients
    0.51
     রোগীর
    0.50
     Patienten
    0.50
     pacient
    0.49
     médicale
    0.47
     assertive
    0.47
    Activations Density 0.001%

    No Known Activations